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

    Neuronpedia

    INDEX
    Explanations

    words that indicate inclusivity or broad accessibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aro
    -0.16
    abler
    -0.14
    arrow
    -0.14
    isco
    -0.14
    ox
    -0.14
    til
    -0.14
    tier
    -0.13
    io
    -0.13
    engo
    -0.13
    ubit
    -0.13
    POSITIVE LOGITS
    Ñĩки
    0.15
     Twin
    0.14
    elib
    0.14
     priority
    0.13
    CRT
    0.13
     Snowden
    0.13
    ỳ
    0.13
    resse
    0.13
    los
    0.13
     terminal
    0.13
    Act Density 0.000%

    No Known Activations