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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating appropriateness or suitability for specific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    InitVars
    -0.73
    ViewFeatures
    -0.73
     Hump
    -0.60
    ATN
    -0.58
    BeginContext
    -0.57
     numberWith
    -0.56
    iyor
    -0.56
     Osorio
    -0.56
    Admins
    -0.56
     cynicism
    -0.55
    POSITIVE LOGITS
     suitable
    2.76
    suitable
    2.61
     Suitable
    2.53
    Suitable
    2.37
     suitability
    1.91
     unsuitable
    1.78
     geschikt
    1.72
    uitable
    1.71
     suited
    1.70
    suited
    1.57
    Act Density 0.051%

    No Known Activations