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

    Neuronpedia

    INDEX
    Explanations

    guidance-related terms or directives

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ells
    -0.77
     Roses
    -0.71
    ols
    -0.70
    itol
    -0.69
    ones
    -0.67
    WC
    -0.65
     forfeit
    -0.64
    Ve
    -0.64
    tein
    -0.64
    Sus
    -0.64
    POSITIVE LOGITS
     guidance
    1.24
     counselor
    0.99
     counselors
    0.93
     guideline
    0.91
     guides
    0.87
     Advice
    0.86
     advising
    0.84
     guiding
    0.84
     guidelines
    0.83
     Guid
    0.82
    Act Density 0.009%

    No Known Activations