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

    Neuronpedia

    INDEX
    Explanations

    references to reciprocity and mutual agreements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sidemargin
    -0.59
    Джерела
    -0.57
    Література
    -0.55
    culares
    -0.46
    dis
    -0.45
    อาด
    -0.45
     пусты
    -0.44
    MoveNext
    -0.43
    openConnection
    -0.43
    POLE
    -0.43
    POSITIVE LOGITS
     reciprocal
    0.97
     reciproc
    0.96
     recipro
    0.83
     reciprocity
    0.74
     Recipro
    0.67
     counterpart
    0.65
    InjectAttribute
    0.63
    reverse
    0.62
     umgekehrt
    0.62
     karş
    0.62
    Act Density 0.406%

    No Known Activations