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

    Neuronpedia

    INDEX
    Explanations

    expressions of enjoyment and pleasure in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    older
    -0.17
    atte
    -0.15
    esar
    -0.15
     enjoying
    -0.14
    owing
    -0.14
    uras
    -0.14
    .rt
    -0.14
    ual
    -0.14
    arin
    -0.14
    ford
    -0.13
    POSITIVE LOGITS
    ably
    0.36
    ment
    0.24
    ments
    0.24
    able
    0.23
     themselves
    0.21
     yourselves
    0.20
    ables
    0.19
    /dis
    0.19
    erals
    0.19
     ourselves
    0.19
    Act Density 0.043%

    No Known Activations