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

    Neuronpedia

    INDEX
    Explanations

    mentions of 'TS' with varying degrees of emphasis

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of "TS" with varying values, likely indicating specific topics or categories related to technology or ratings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ston
    -0.82
    stein
    -0.80
    liest
    -0.76
    hander
    -0.70
    ances
    -0.69
    meat
    -0.68
    esville
    -0.67
    ously
    -0.67
    bow
    -0.65
     joke
    -0.65
    POSITIVE LOGITS
    weet
    0.99
    ypes
    0.94
    BUR
    0.90
    ullivan
    0.90
    WER
    0.89
    ICLE
    0.87
    REE
    0.87
    ocial
    0.86
    EC
    0.85
    EMP
    0.85
    Act Density 0.023%

    No Known Activations