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

    Neuronpedia

    INDEX
    Explanations

    terms related to appropriateness or suitability

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

    fitting, appropriate, suitable

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     yolu
    -0.40
    Highly
    -0.39
     decisiones
    -0.39
     tightly
    -0.38
    Autoritní
    -0.37
     procesos
    -0.37
     Mitarbeit
    -0.36
     blindly
    -0.35
    highly
    -0.35
     []:
    -0.35
    POSITIVE LOGITS
    ContentAlignment
    0.78
     fitting
    0.71
    WriteTagHelper
    0.66
     Fitting
    0.62
     appropriate
    0.61
     appropriately
    0.57
    Vidite
    0.57
     suitably
    0.57
     proper
    0.56
     suitable
    0.56
    Act Density 0.022%

    No Known Activations