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

    Neuronpedia

    INDEX
    Explanations

    terms related to controversial or illegal activities involving violence or corruption

    oai_token-act-pair · gpt-3.5-turbo

    terms related to violence and abusive behaviors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alg
    -0.85
    aird
    -0.85
    erald
    -0.74
     Indigo
    -0.73
    stellar
    -0.70
     Daylight
    -0.69
     Balance
    -0.68
    foreseen
    -0.67
     Rockies
    -0.65
    alsa
    -0.65
    POSITIVE LOGITS
     blackmail
    1.11
     intimidation
    1.10
     spying
    1.01
     tactics
    0.99
     coercion
    0.99
     coercive
    0.96
     extortion
    0.96
     harassing
    0.94
     perpetrated
    0.93
     abusing
    0.92
    Act Density 0.410%

    No Known Activations