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

    Neuronpedia

    INDEX
    Explanations

    sequences of numbers and characters

    oai_token-act-pair · gpt-3.5-turbo

    sequences of numbers and their repetitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    awaru
    -0.78
    etz
    -0.70
    rolet
    -0.67
    efully
    -0.63
    uated
    -0.63
    gerald
    -0.63
    ured
    -0.62
     sway
    -0.62
    lehem
    -0.62
    urat
    -0.62
    POSITIVE LOGITS
    nd
    1.93
    ND
    1.08
     thirds
    1.00
    147
    0.96
    ½
    0.96
    160
    0.95
    133
    0.94
    187
    0.89
     externalToEVAOnly
    0.88
    245
    0.86
    Act Density 0.129%

    No Known Activations