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

    Neuronpedia

    INDEX
    Explanations

    references to specific experiments or technical procedures

    oai_token-act-pair · gpt-3.5-turbo

    terms related to military operations or strategic approaches

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hower
    -0.91
    KEN
    -0.85
    KING
    -0.79
    oÄŁan
    -0.78
    ipeg
    -0.78
     Shake
    -0.71
    WIND
    -0.70
     GOODMAN
    -0.70
    RAY
    -0.70
    MH
    -0.69
    POSITIVE LOGITS
    atus
    1.31
    orum
    1.31
    ensis
    1.29
    inis
    1.20
    anus
    1.16
    iae
    1.15
    arius
    1.15
    ibus
    1.13
    ius
    1.13
    orem
    1.11
    Act Density 0.548%

    No Known Activations