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

    Neuronpedia

    INDEX
    Explanations

    occurrences of guilt and legal accountability in criminal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    awah
    -0.16
     Dou
    -0.15
     dood
    -0.15
    ither
    -0.15
    rost
    -0.14
     arte
    -0.14
    quette
    -0.14
     tit
    -0.14
    anut
    -0.14
    tat
    -0.13
    POSITIVE LOGITS
    Ĥ¬
    0.18
    ustil
    0.16
    prus
    0.14
    ÐŁÐļ
    0.14
    /fw
    0.14
    ramid
    0.13
    INDER
    0.13
    bject
    0.13
    áŀ¶áŀ
    0.13
    utorial
    0.13
    Act Density 0.015%

    No Known Activations