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

    Neuronpedia

    INDEX
    Explanations

    upper-case 'I' with a numeral attached to it

    oai_token-act-pair · gpt-3.5-turbo

    the first-person pronoun "I"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    imentary
    -0.69
    halla
    -0.66
    theless
    -0.65
    ded
    -0.61
     combustion
    -0.61
    ruciating
    -0.59
     cov
    -0.59
    rooms
    -0.59
    lined
    -0.58
    ription
    -0.57
    POSITIVE LOGITS
    AMI
    1.09
    YA
    1.04
    OUS
    1.03
    BILITY
    1.02
    ANS
    0.99
    BA
    0.96
    KE
    0.95
    RECT
    0.93
    ALLY
    0.92
    US
    0.91
    Act Density 0.029%

    No Known Activations