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

    Neuronpedia

    INDEX
    Explanations

    references to kisses and related actions or expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hurst
    -0.18
    493
    -0.16
    bens
    -0.15
    unto
    -0.15
    zag
    -0.14
    Picker
    -0.14
    east
    -0.14
    hift
    -0.14
    antom
    -0.14
    552
    -0.14
    POSITIVE LOGITS
     Kiss
    0.30
     kiss
    0.27
     goodbye
    0.24
     kissed
    0.20
     kissing
    0.20
     Lips
    0.19
    (es
    0.19
     lips
    0.19
     Lip
    0.18
     hello
    0.17
    Act Density 0.013%

    No Known Activations