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

    Neuronpedia

    INDEX
    Explanations

    measurements of distance

    oai_token-act-pair · gpt-3.5-turbo

    parentheses and numerical values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Zeit
    -0.72
     lax
    -0.72
     Daw
    -0.71
     buddy
    -0.69
     Nit
    -0.67
     Nut
    -0.65
     Bees
    -0.65
     Crow
    -0.65
     expire
    -0.64
    edIn
    -0.63
    POSITIVE LOGITS
    sic
    1.21
    approximately
    1.19
    formerly
    1.13
    excluding
    1.11
    including
    1.07
    pictured
    0.98
    âĢ¦)
    0.98
    more
    0.96
    depending
    0.95
    fourth
    0.95
    Act Density 0.052%

    No Known Activations