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

    Neuronpedia

    INDEX
    Explanations

    personal opinions or perspectives expressed by the speaker

    oai_token-act-pair · gpt-3.5-turbo

    expressions centered around personal perspective and experience

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lycer
    -0.79
    raviolet
    -0.76
     Towns
    -0.64
    batch
    -0.64
    roup
    -0.61
     Equality
    -0.60
     Finish
    -0.59
    SOURCE
    -0.59
     TMZ
    -0.58
     Fors
    -0.57
    POSITIVE LOGITS
    adow
    1.06
    adows
    1.01
     personally
    0.98
    OGR
    0.84
    asured
    0.78
    imei
    0.77
     dear
    0.73
    utral
    0.73
    eker
    0.72
    cca
    0.72
    Act Density 0.041%

    No Known Activations