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

    Neuronpedia

    INDEX
    Explanations

    phrases related to getting away with something

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to getting away with actions or behaviors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arta
    -0.87
    wang
    -0.82
    atform
    -0.79
    ural
    -0.74
    agues
    -0.72
    stem
    -0.72
    ready
    -0.71
    wake
    -0.69
    sonian
    -0.68
     Ahead
    -0.68
    POSITIVE LOGITS
     murder
    1.05
     murdering
    0.96
     mischief
    0.91
     manslaughter
    0.90
     immoral
    0.89
     careless
    0.87
     reckless
    0.86
     anything
    0.86
     impunity
    0.85
     exploiting
    0.85
    Act Density 0.081%

    No Known Activations