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

    Neuronpedia

    INDEX
    Explanations

    words related to regulating, restricting, or limiting actions or behaviors

    oai_token-act-pair · gpt-3.5-turbo

    terminology related to restriction or limitation of rights and resources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    FORE
    -0.79
    acht
    -0.73
    ublic
    -0.70
    Äĩ
    -0.69
    æ©
    -0.67
    Sham
    -0.66
    owitz
    -0.66
    OF
    -0.65
    ashington
    -0.65
    ellow
    -0.64
    POSITIVE LOGITS
    ively
    0.93
    orously
    0.85
     mobility
    0.84
    ŃĶ
    0.80
     visibility
    0.77
     access
    0.76
     fragmentation
    0.75
     adherence
    0.73
    imize
    0.73
    iple
    0.73
    Act Density 0.045%

    No Known Activations