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

    Neuronpedia

    INDEX
    Explanations

    discussions about personal favorites and preferences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ibri
    -0.17
    ienda
    -0.14
     ourselves
    -0.14
    prar
    -0.14
    vertising
    -0.13
     Apparently
    -0.13
    úsqueda
    -0.13
     prostÅĻednictvÃŃm
    -0.12
    igid
    -0.12
    ysterious
    -0.12
    POSITIVE LOGITS
     hands
    0.50
    Hands
    0.40
    hands
    0.39
     Hands
    0.38
     HAND
    0.30
     easily
    0.30
     Easily
    0.29
     favorite
    0.27
     manos
    0.26
     favourite
    0.25
    Act Density 0.160%

    No Known Activations