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

    Neuronpedia

    INDEX
    Explanations

    words associated with the act of exploration and engagement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    emem
    -0.16
    apg
    -0.15
    azor
    -0.15
    á»iji
    -0.15
    spm
    -0.15
    Coin
    -0.15
    ogie
    -0.14
    enha
    -0.14
    ocol
    -0.14
    Ñģол
    -0.14
    POSITIVE LOGITS
     into
    0.30
     deeper
    0.21
    ovich
    0.20
     INTO
    0.18
    t
    0.18
    Into
    0.18
     Into
    0.18
    into
    0.16
    .into
    0.16
    gence
    0.16
    Act Density 0.004%

    No Known Activations