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
    ikal
    -0.16
    oria
    -0.16
    elim
    -0.15
    ɵ
    -0.15
    hausen
    -0.15
    inen
    -0.15
    zug
    -0.15
    yll
    -0.15
    elin
    -0.14
    oman
    -0.14
    POSITIVE LOGITS
    ampo
    0.18
    tol
    0.17
    452
    0.16
    /mit
    0.14
    à¥įह
    0.14
    ulet
    0.14
    och
    0.14
    ëį°ìĿ´íĬ¸
    0.14
    ftime
    0.14
    ruba
    0.14
    Act Density 0.015%

    No Known Activations