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

    Neuronpedia

    INDEX
    Explanations

    legal references and numbered sections within documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <b>
    -0.76
     </
    -0.70
    ص
    -0.69
     pick
    -0.68
    das
    -0.68
     Whal
    -0.66
    </
    -0.66
    เป
    -0.64
    tes
    -0.64
    ناد
    -0.64
    POSITIVE LOGITS
     II
    1.53
    II
    1.45
    III
    1.37
     III
    1.30
     VIII
    1.23
    IIII
    1.20
     VII
    1.19
     ii
    1.16
    IIA
    1.14
    VII
    1.11
    Act Density 0.134%

    No Known Activations