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

    Neuronpedia

    INDEX
    Explanations

    words related to coercion and compelling actions through force

    oai_token-act-pair · gpt-3.5-turbo

    terms and phrases related to coercion and control

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gal
    -0.81
    hop
    -0.81
     Ion
    -0.80
    dream
    -0.76
    Hop
    -0.74
    Dream
    -0.73
     Blessed
    -0.73
    arks
    -0.73
    Found
    -0.72
    mort
    -0.71
    POSITIVE LOGITS
     coer
    1.10
     coerced
    1.06
     coercion
    0.99
     compel
    0.85
     coercive
    0.83
     coerc
    0.81
     pressuring
    0.78
    glers
    0.77
     blackmail
    0.76
     compulsion
    0.76
    Act Density 0.027%

    No Known Activations