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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a particular thought, feeling, or perspective

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to perceptions or feelings about situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oute
    -0.77
    ynski
    -0.77
    uster
    -0.74
    usters
    -0.72
    ividual
    -0.71
     sugg
    -0.71
    erville
    -0.70
    etheus
    -0.69
    ewitness
    -0.66
    iners
    -0.64
    POSITIVE LOGITS
    fare
    0.85
    ward
    0.71
    forward
    0.69
     forever
    0.68
    ï¸
    0.66
    lier
    0.65
    bill
    0.64
    fitting
    0.64
    footed
    0.64
    WARD
    0.64
    Act Density 0.038%

    No Known Activations