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

    Neuronpedia

    INDEX
    Explanations

    expressions of liking or preferences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ंदीखरीदारी
    -0.81
    pulumi
    -0.64
    TestingModule
    -0.64
    devServer
    -0.63
    pub
    -0.63
     Guerrero
    -0.61
     Asher
    -0.61
    se
    -0.60
    envolvimento
    -0.59
    dymyr
    -0.59
    POSITIVE LOGITS
    empio
    0.83
     LIKE
    0.82
    Likes
    0.77
     Likes
    0.76
    dislike
    0.74
     Liked
    0.73
     liked
    0.70
    LIKE
    0.70
    likes
    0.70
     Мексичка
    0.67
    Act Density 0.038%

    No Known Activations