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

    Neuronpedia

    INDEX
    Explanations

    phrases related to sources of information or authority

    oai_token-act-pair · gpt-3.5-turbo

    phrases that convey reliance on evidence or data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    icably
    -0.71
    ilyn
    -0.70
    assies
    -0.70
    "]=>
    -0.69
    ovember
    -0.68
    icer
    -0.67
    anke
    -0.67
    mos
    -0.66
    etsk
    -0.66
    ipeg
    -0.66
    POSITIVE LOGITS
     assumption
    1.08
     premise
    0.98
     principles
    0.96
     principle
    0.92
     criteria
    0.87
     whims
    0.87
     assumptions
    0.86
     methodology
    0.83
     standpoint
    0.80
     hypothesis
    0.78
    Act Density 0.313%

    No Known Activations