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

    Neuronpedia

    INDEX
    Explanations

    words related to acceptance and rejection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    VIAF
    -0.67
     "..\..\..\
    -0.57
    newArrayList
    -0.57
     חיצוניים
    -0.56
    modium
    -0.55
     gql
    -0.55
    Korn
    -0.54
    IUrlHelper
    -0.54
    InputBorder
    -0.54
    mingen
    -0.54
    POSITIVE LOGITS
     accepts
    1.14
     Accept
    1.13
     accept
    1.11
     Accepting
    1.06
    ACCEPT
    1.02
     accepting
    1.00
    accepts
    0.95
     ACCEPT
    0.95
    Accept
    0.93
    accept
    0.92
    Act Density 0.119%

    No Known Activations