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

    Neuronpedia

    INDEX
    Explanations

    words indicating health-related conditions and actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orem
    -0.28
    oret
    -0.20
    iming
    -0.18
    cest
    -0.17
    grily
    -0.17
    oretical
    -0.16
    quoi
    -0.15
    visa
    -0.15
    rone
    -0.14
    ÑģÑİ
    -0.14
    POSITIVE LOGITS
    /of
    0.17
    MRI
    0.16
    bidden
    0.15
    DNA
    0.15
    plevel
    0.15
    pired
    0.14
    cribes
    0.14
     Gesch
    0.14
    cribed
    0.14
    Tube
    0.14
    Act Density 0.531%

    No Known Activations