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

    Neuronpedia

    INDEX
    Explanations

    references to relationships or interactions between two parties

    oai_token-act-pair · gpt-3.5-turbo

    references to relationships involving two entities or parties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aukee
    -0.82
    ugu
    -0.77
    racuse
    -0.76
    Grade
    -0.73
     Caption
    -0.71
    fw
    -0.71
    atown
    -0.70
     srf
    -0.69
    osponsors
    -0.67
    ubs
    -0.66
    POSITIVE LOGITS
     thirds
    1.06
     halves
    0.98
     sexes
    0.89
    fold
    0.84
    teenth
    0.81
     brothers
    0.79
     dozen
    0.72
     decades
    0.72
    een
    0.72
     weeks
    0.71
    Act Density 0.088%

    No Known Activations