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

    Neuronpedia

    INDEX
    Explanations

    key adjectives and phrases indicating significant events or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    //{{
    -0.21
    AndView
    -0.17
    ÑĥÑī
    -0.17
    .infinity
    -0.16
    elden
    -0.15
    iali
    -0.15
    rvine
    -0.14
     Incontri
    -0.14
     undef
    -0.14
    oins
    -0.14
    POSITIVE LOGITS
    omas
    0.16
    eros
    0.16
    igo
    0.15
    ets
    0.15
    ohl
    0.15
    ager
    0.14
    .fil
    0.14
    erot
    0.14
    agus
    0.14
    ικά
    0.14
    Act Density 0.002%

    No Known Activations