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

    Neuronpedia

    INDEX
    Explanations

    phrases asking about or referring to a specific method or approach

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a particular manner or approach to situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    usters
    -0.77
     livest
    -0.75
    uster
    -0.73
     sugg
    -0.68
    urated
    -0.67
    ividual
    -0.64
    nect
    -0.63
    urate
    -0.63
    ynski
    -0.62
     cryst
    -0.62
    POSITIVE LOGITS
    fare
    1.19
    ward
    1.09
    finding
    1.07
    WARD
    0.92
    bill
    0.84
    point
    0.84
    forward
    0.83
    finder
    0.81
    points
    0.77
    Jet
    0.73
    Act Density 0.048%

    No Known Activations