Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    API-related terminology and discussions about their effectiveness or sufficiency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Follows words indicating inadequacy or failure

    np_acts-logits-general · gemini-2.0-flash

    lack of sufficiency or effectiveness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     محفوظة
    -0.48
     esternos
    -0.47
    routeProvider
    -0.44
    Hentet
    -0.42
    WriteBarrier
    -0.42
    ItemBackground
    -0.42
    RTSC
    -0.41
     Walkover
    -0.40
    ValueStyle
    -0.40
    帖最后由
    -0.40
    POSITIVE LOGITS
     unsatisfactory
    0.79
     inadequate
    0.69
     unsuitable
    0.63
     insufficient
    0.61
     insufic
    0.55
     ineffective
    0.55
     incomplete
    0.54
     yeter
    0.54
    不夠
    0.53
     Inadequate
    0.52
    Act Density 0.826%

    No Known Activations