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

    Neuronpedia

    INDEX
    Explanations

    words related to tolerance and acceptance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wald
    -0.19
    -ÑĤо
    -0.18
    reon
    -0.17
    elow
    -0.17
    aldi
    -0.17
    lined
    -0.17
    lify
    -0.16
    dra
    -0.16
    dit
    -0.16
    minster
    -0.16
    POSITIVE LOGITS
    swagen
    0.18
    hevik
    0.16
    unteer
    0.16
    彩
    0.15
    aison
    0.15
    ī
    0.15
    te
    0.15
    tej
    0.15
    pedia
    0.15
    ocaust
    0.15
    Act Density 0.079%

    No Known Activations