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

    Neuronpedia

    INDEX
    Explanations

    accent characters, possibly related to specific languages or textual encoding

    oai_token-act-pair · gpt-3.5-turbo

    special characters or symbols in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    matically
    -0.78
    ependence
    -0.75
    sterdam
    -0.71
    */(
    -0.70
    ciating
    -0.69
    versions
    -0.68
    ifice
    -0.67
     Vinyl
    -0.67
    swick
    -0.67
     Virgin
    -0.66
    POSITIVE LOGITS
    º
    1.21
    α
    1.00
    DAY
    0.85
    oti
    0.85
    ε
    0.77
    117
    0.77
    µ
    0.77
    Ĺ
    0.76
    çĶŁ
    0.75
    ³
    0.75
    Act Density 0.006%

    No Known Activations