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

    Neuronpedia

    INDEX
    Explanations

    unique patterns of characters or symbol sequences that seem to be specific identifiers or acronyms related to organizations, locations, or events

    oai_token-act-pair · gpt-3.5-turbo

    specific formal organizations or associations mentioned in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     gent
    -0.82
     revol
    -0.81
     Freak
    -0.76
     gorge
    -0.75
     everywhere
    -0.72
     lur
    -0.71
     lurking
    -0.69
     persu
    -0.68
     unpopular
    -0.68
     polit
    -0.68
    POSITIVE LOGITS
    Additionally
    1.15
    However
    1.02
     Additionally
    1.01
    sequently
    0.98
    Alternatively
    0.96
     Alternatively
    0.95
    Therefore
    0.94
    Refer
    0.94
    According
    0.93
    Additional
    0.93
    Act Density 0.949%

    No Known Activations