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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude and appreciation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    roperty
    -0.16
    ount
    -0.16
    缮
    -0.16
    ereotype
    -0.16
    lik
    -0.15
    IX
    -0.15
     olsa
    -0.15
    è·¡
    -0.14
    obby
    -0.14
    perm
    -0.14
    POSITIVE LOGITS
    ably
    0.17
    agus
    0.14
    ances
    0.14
     âĹĦ
    0.14
    valuation
    0.14
    iable
    0.14
    cak
    0.14
    -minded
    0.14
    writeln
    0.14
    agements
    0.13
    Act Density 0.015%

    No Known Activations