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

    Neuronpedia

    INDEX
    Explanations

    terms associated with abusive behaviors and situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rei
    -0.17
    vid
    -0.15
    ference
    -0.15
    apsed
    -0.15
    تاÙĨ
    -0.15
    ller
    -0.15
     ucwords
    -0.14
    ari
    -0.14
    strand
    -0.14
    ìķ¡
    -0.14
    POSITIVE LOGITS
     Dhabi
    0.20
    ulent
    0.17
    antium
    0.16
    anas
    0.15
    DED
    0.15
    еÑĢп
    0.15
    antly
    0.15
    ulo
    0.14
    該
    0.14
    ys
    0.14
    Act Density 0.009%

    No Known Activations