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

    Neuronpedia

    INDEX
    Explanations

    special characters and symbols

    oai_token-act-pair · gpt-3.5-turbo

    the presence of special character tokens or formatting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ciating
    -1.12
    swick
    -0.94
    illac
    -0.85
    sterdam
    -0.83
    matically
    -0.82
    matical
    -0.74
    brates
    -0.74
    teness
    -0.70
    frey
    -0.70
    ependence
    -0.68
    POSITIVE LOGITS
    oti
    0.98
    uri
    0.85
    orter
    0.84
    abba
    0.81
    α
    0.81
    uler
    0.80
    Å«
    0.76
    uli
    0.76
    orts
    0.75
    Exit
    0.74
    Act Density 0.028%

    No Known Activations