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

    Neuronpedia

    INDEX
    Explanations

    terms related to tampering, especially with medications and evidence

    oai_token-act-pair · gpt-3.5-turbo

    terms related to social issues and tampering

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Annotations
    -0.81
    trap
    -0.76
     Dome
    -0.74
    DragonMagazine
    -0.74
    lust
    -0.71
    é¾
    -0.70
     Prospect
    -0.70
    schild
    -0.69
     Grail
    -0.68
    outube
    -0.68
    POSITIVE LOGITS
    ģ
    0.92
    pper
    0.88
    ating
    0.85
    esthes
    0.84
    aton
    0.83
    emaker
    0.83
    erer
    0.82
    esthetic
    0.81
    ographed
    0.81
    pped
    0.80
    Act Density 0.018%

    No Known Activations