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

    Neuronpedia

    INDEX
    Explanations

    trends involving increases or decreases in various metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abis
    -0.15
    owski
    -0.15
    _NC
    -0.15
    è¹
    -0.14
    owe
    -0.14
    macı
    -0.14
    akes
    -0.14
    memberof
    -0.14
    linkplain
    -0.14
    ylene
    -0.14
    POSITIVE LOGITS
    unft
    0.16
    chants
    0.16
    slaught
    0.16
    ãĥ¼ãĥ³
    0.15
    ecast
    0.15
    \Id
    0.15
    istrovstvÃŃ
    0.15
    prung
    0.14
    AINS
    0.14
    ered
    0.14
    Act Density 0.108%

    No Known Activations