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

    Neuronpedia

    INDEX
    Explanations

    activities related to scams or illegal activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enty
    -0.15
     dissert
    -0.14
    ursions
    -0.14
    loor
    -0.14
    eref
    -0.14
    zı
    -0.14
     Crane
    -0.14
    psc
    -0.14
    aversal
    -0.13
    theon
    -0.13
    POSITIVE LOGITS
     artificial
    0.15
    hausen
    0.15
     Artificial
    0.14
    avo
    0.14
    hg
    0.13
    Ïĩα
    0.13
    YG
    0.13
    hai
    0.13
    ableOpacity
    0.13
    shake
    0.13
    Act Density 0.025%

    No Known Activations