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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a temporal relationship

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     estekak
    -0.77
    الإنجليزية
    -0.69
     '\''
    -0.63
     fortn
    -0.61
    transQ
    -0.61
     Amore
    -0.58
     Seton
    -0.58
    enumii
    -0.57
     endblock
    -0.54
    ApiProperty
    -0.54
    POSITIVE LOGITS
     мәкал
    0.53
     муніципалі
    0.52
    RefNanny
    0.51
     świ
    0.47
     reserve
    0.47
     reserva
    0.47
     çe
    0.46
     préf
    0.46
    ValueGeneration
    0.45
     ahead
    0.45
    Act Density 0.161%

    No Known Activations