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

    Neuronpedia

    INDEX
    Explanations

    words related to physical and environmental changes/actions

    oai_token-act-pair · gpt-3.5-turbo

    letters or single characters that may represent various abbreviations or codes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ô
    -0.87
    FUL
    -0.82
     Abyss
    -0.74
    stellar
    -0.72
    _>
    -0.72
     Bohem
    -0.72
     Pwr
    -0.71
     Say
    -0.69
    Credits
    -0.66
    theless
    -0.64
    POSITIVE LOGITS
    ancies
    1.08
    odes
    1.06
    ams
    0.95
    vers
    0.94
    acts
    0.94
    ules
    0.93
    ippers
    0.92
    otypes
    0.92
    ule
    0.92
    icion
    0.91
    Act Density 0.350%

    No Known Activations