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

    Neuronpedia

    INDEX
    Explanations

    phrases related to allowing or giving permission

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     LoggerFactory
    -0.65
    AssignableFrom
    -0.47
    ungszeit
    -0.45
     need
    -0.44
     wirst
    -0.43
    сур
    -0.43
    need
    -0.43
    isOk
    -0.42
     suddenly
    -0.42
     must
    -0.42
    POSITIVE LOGITS
    UserScript
    0.85
    principalColumn
    0.73
     estekak
    0.69
     ProtoMessage
    0.67
     IndexPath
    0.65
     lapse
    0.63
    ArgsConstructor
    0.63
     nahilalakip
    0.63
     slide
    0.62
    KommentareTeilen
    0.61
    Act Density 0.160%

    No Known Activations