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

    Neuronpedia

    INDEX
    Explanations

    words related to mutation, specifically with a focus on "mut" and "mutate"

    oai_token-act-pair · gpt-3.5-turbo

    references to mutilation, particularly in the context of gender-based violence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Defenders
    -0.89
    ACP
    -0.78
    ¯¯
    -0.76
    ħĭ
    -0.74
    ulhu
    -0.71
    ï¸
    -0.69
     Desk
    -0.68
    zzo
    -0.64
    ngth
    -0.64
     Morning
    -0.63
    POSITIVE LOGITS
    iple
    1.20
    iny
    0.95
    agen
    0.93
    ually
    0.92
    atis
    0.90
    ations
    0.89
    ilation
    0.88
    mut
    0.83
    reating
    0.82
    tering
    0.82
    Act Density 0.010%

    No Known Activations