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

    Neuronpedia

    INDEX
    Explanations

    percentage values mentioned in a sentence

    oai_token-act-pair · gpt-3.5-turbo

    percentage values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Constantin
    -0.66
     bount
    -0.61
     tyrann
    -0.60
     patriarch
    -0.59
    iris
    -0.58
     corpus
    -0.58
     lun
    -0.57
     miniature
    -0.55
     skelet
    -0.55
     fork
    -0.55
    POSITIVE LOGITS
    ooters
    0.98
    iversary
    0.81
    ordable
    0.78
    orgetown
    0.74
    okers
    0.73
    olson
    0.73
    asper
    0.73
    iliar
    0.71
    iewicz
    0.71
    ulty
    0.70
    Act Density 0.043%

    No Known Activations