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

    Neuronpedia

    INDEX
    Explanations

    statements indicating the presence or absence of evidence or suggestions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a lack of evidence or denial of claims

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cellaneous
    -0.70
    ione
    -0.67
    è»
    -0.65
    Boss
    -0.65
    Dialogue
    -0.63
    izont
    -0.63
    inic
    -0.62
     Pieces
    -0.61
    feet
    -0.61
     largeDownload
    -0.61
    POSITIVE LOGITS
     anymore
    1.05
     slightest
    0.91
     anyone
    0.86
     bothered
    0.84
     contradicts
    0.84
     whatsoever
    0.82
     justifies
    0.81
     anybody
    0.79
     anything
    0.77
     bothers
    0.76
    Act Density 0.158%

    No Known Activations