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

    Neuronpedia

    INDEX
    Explanations

    phrases related to limits and boundaries

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to limits and constraints

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    outine
    -0.77
    catentry
    -0.73
    igious
    -0.73
    anto
    -0.72
    QL
    -0.69
    icultural
    -0.69
    ploma
    -0.67
    ussian
    -0.66
     subsistence
    -0.66
    ategor
    -0.64
    POSITIVE LOGITS
     slack
    0.82
     brim
    0.81
     swung
    0.77
     tightening
    0.74
     boiling
    0.72
     thin
    0.72
     peeled
    0.71
     crystal
    0.71
     shifted
    0.70
     ticking
    0.70
    Act Density 0.389%

    No Known Activations