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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "like" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    es
    -0.60
    se
    -0.60
    ES
    -0.56
    dojo
    -0.51
    innerHeight
    -0.51
     considérons
    -0.51
    cipe
    -0.49
     الإسلام
    -0.49
    ses
    -0.49
    en
    -0.49
    POSITIVE LOGITS
    liest
    1.01
     LIKE
    0.97
    LIKE
    0.94
    lihood
    0.93
    like
    0.88
    WISE
    0.87
    lier
    0.86
     minded
    0.84
    Like
    0.84
    wiſe
    0.83
    Act Density 0.100%

    No Known Activations