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

    Neuronpedia

    INDEX
    Explanations

    terms that indicate frequency or prevalence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     يتيمه
    -0.68
     ConstraintSet
    -0.66
    rbrakk
    -0.62
    parsedMessage
    -0.62
    fjspx
    -0.61
     Superhosts
    -0.60
    tagHelperRunner
    -0.57
    səhifə
    -0.57
     ब्रेकडाउन
    -0.56
    majánló
    -0.56
    POSITIVE LOGITS
     best
    0.67
    best
    0.66
     biggest
    0.63
     safest
    0.59
    biggest
    0.59
     weakest
    0.58
     largest
    0.55
    Best
    0.55
     가장
    0.54
    most
    0.53
    Act Density 0.385%

    No Known Activations