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

    Neuronpedia

    INDEX
    Explanations

    verbs or phrases related to bypassing or circumventing obstacles or rules

    oai_token-act-pair · gpt-3.5-turbo

    terms related to evasion or avoidance of rules and protocols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ankind
    -0.73
    ectar
    -0.72
    Kind
    -0.71
    umble
    -0.70
    opter
    -0.70
    aster
    -0.66
    aws
    -0.65
    killer
    -0.63
    soType
    -0.63
    NAS
    -0.63
    POSITIVE LOGITS
     bypass
    0.95
    edIn
    0.89
    ed
    0.89
    es
    0.84
    ricular
    0.82
    ibility
    0.81
    ing
    0.80
    ibly
    0.80
    esville
    0.75
    ioned
    0.72
    Act Density 0.016%

    No Known Activations