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

    Neuronpedia

    INDEX
    Explanations

    terms related to representation and reflection of themes or ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    liness
    -0.16
    ktop
    -0.16
    ady
    -0.16
    ery
    -0.15
    igan
    -0.15
    sworth
    -0.15
    .Callback
    -0.15
    pered
    -0.14
    .meta
    -0.14
    emi
    -0.14
    POSITIVE LOGITS
    ively
    0.17
    bine
    0.15
    -thinking
    0.14
    .TypeOf
    0.14
    vanished
    0.14
    vál
    0.14
    Ïģά
    0.14
    atile
    0.14
    uate
    0.13
    ิà¸ĩ
    0.13
    Act Density 0.028%

    No Known Activations