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

    Neuronpedia

    INDEX
    Explanations

    instances of agreement or consensus within a context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /dr
    -0.15
    ackson
    -0.15
    oms
    -0.14
    ny
    -0.14
    rose
    -0.14
    ogr
    -0.13
    erman
    -0.13
    aco
    -0.13
    most
    -0.13
    atsu
    -0.13
    POSITIVE LOGITS
    ably
    0.20
    /dis
    0.17
    odÃŃ
    0.16
    大åĪ©
    0.15
    pt
    0.15
    emetery
    0.15
    Ñĥди
    0.14
    ä¿Ĺ
    0.14
    vailable
    0.14
    ments
    0.14
    Act Density 0.042%

    No Known Activations