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

    Neuronpedia

    INDEX
    Explanations

    sequences of unrecognizable characters

    oai_token-act-pair · gpt-3.5-turbo

    various symbols and characters in different scripts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elsen
    -0.84
    hower
    -0.84
    onomy
    -0.76
    urers
    -0.74
    urally
    -0.74
    ividual
    -0.72
    enegger
    -0.72
    ettings
    -0.71
    sonian
    -0.68
    abase
    -0.68
    POSITIVE LOGITS
    °
    1.00
    ®
    0.97
    Ĩ
    0.97
    İ
    0.97
    į
    0.97
    ा
    0.96
    ¾
    0.95
    ¯
    0.93
    ´
    0.91
    ·
    0.91
    Act Density 0.005%

    No Known Activations