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

    Neuronpedia

    INDEX
    Explanations

    expressions of love and affection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ullo
    -0.15
    .tom
    -0.15
    owl
    -0.14
     çĽ
    -0.14
    avour
    -0.14
    udi
    -0.14
    igen
    -0.14
    forgettable
    -0.14
    ensors
    -0.14
    avor
    -0.14
    POSITIVE LOGITS
    abilia
    0.19
    jer
    0.17
     guts
    0.17
    iggins
    0.15
    isu
    0.15
     coraz
    0.15
     deeply
    0.15
    ÛĮس
    0.14
    á»Ļ
    0.14
     enough
    0.14
    Act Density 0.087%

    No Known Activations