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

    Neuronpedia

    INDEX
    Explanations

    words related to superlatives and registrations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to illustration and registration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    externalActionCode
    -0.78
     Blow
    -0.73
     Hole
    -0.72
     Speech
    -0.72
    hunt
    -0.72
    xual
    -0.71
     Tone
    -0.69
     Hearing
    -0.66
     Tunnel
    -0.65
    stem
    -0.65
    POSITIVE LOGITS
    ines
    1.09
    rator
    1.05
    inals
    1.04
    rative
    1.04
    rators
    0.99
    inations
    0.98
    rit
    0.95
    aneous
    0.94
    irmed
    0.92
    ined
    0.90
    Act Density 0.033%

    No Known Activations