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

    Neuronpedia

    INDEX
    Explanations

    proper nouns referring to specific individuals

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "whom."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    belt
    -0.73
    âĨ
    -0.70
    Loading
    -0.70
    reach
    -0.67
     Belt
    -0.66
    boot
    -0.66
    pad
    -0.65
    aster
    -0.65
    hands
    -0.63
    Charg
    -0.63
    POSITIVE LOGITS
    soever
    1.95
    izens
    0.77
    umbnails
    0.77
    odox
    0.76
    ispers
    0.74
    omever
    0.73
    igham
    0.71
     coh
    0.70
    racuse
    0.68
    asar
    0.68
    Act Density 0.008%

    No Known Activations