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

    Neuronpedia

    INDEX
    Explanations

    code syntax with special characters

    oai_token-act-pair · gpt-3.5-turbo

    symbols or characters that indicate a specific format or structure in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etheless
    -0.93
    İĭ
    -0.88
     destro
    -0.82
    onial
    -0.81
    entimes
    -0.79
    yssey
    -0.78
    erville
    -0.78
    oria
    -0.76
    teenth
    -0.75
    orpor
    -0.74
    POSITIVE LOGITS
    _>
    1.42
    =>
    0.89
    PsyNetMessage
    0.82
    ablishment
    0.74
     >
    0.70
    .<
    0.70
    tf
    0.69
    ++++
    0.68
    ALL
    0.68
    PO
    0.66
    Act Density 0.022%

    No Known Activations