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

    Neuronpedia

    INDEX
    Explanations

    expressions related to determining optimal or best approaches

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

    best way to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     avoient
    -0.65
     Infór
    -0.62
     étoient
    -0.60
     myſelf
    -0.60
     feroit
    -0.59
     auroit
    -0.59
    windowFixed
    -0.57
    TypedDataSet
    -0.57
     AssemblyProduct
    -0.57
     CreateTagHelper
    -0.56
    POSITIVE LOGITS
     best
    0.65
    Best
    0.52
     Best
    0.49
    best
    0.49
     meglio
    0.47
     optimally
    0.46
     mieux
    0.43
     bäst
    0.43
     mejor
    0.42
     better
    0.40
    Act Density 0.005%

    No Known Activations