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

    Neuronpedia

    INDEX
    Explanations

    violations of laws or regulations

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to violations of laws or rights

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    onna
    -0.86
    mad
    -0.82
    affer
    -0.75
    deb
    -0.74
    venture
    -0.69
    FORE
    -0.67
    issue
    -0.67
    timer
    -0.66
    rikes
    -0.66
    ael
    -0.66
    POSITIVE LOGITS
     unfocusedRange
    0.96
    orius
    0.76
    İĭ
    0.74
     violating
    0.68
    ingly
    0.67
    seless
    0.66
     violations
    0.65
     Behavior
    0.64
     stereotypes
    0.64
     Nielsen
    0.63
    Act Density 0.080%

    No Known Activations