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

    Neuronpedia

    INDEX
    Explanations

    instances where something is very clear or obvious

    oai_token-act-pair · gpt-3.5-turbo

    the word "evident" and its variants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    berman
    -0.84
    pton
    -0.74
    pered
    -0.72
    create
    -0.72
    fing
    -0.71
    EStreamFrame
    -0.70
    zanne
    -0.69
    scribe
    -0.69
    atern
    -0.68
    prime
    -0.66
    POSITIVE LOGITS
    iary
    1.36
     evident
    0.89
    ial
    0.80
     Signs
    0.75
     signs
    0.73
    wcsstore
    0.72
    iation
    0.72
    icative
    0.72
    ances
    0.71
    IFIED
    0.71
    Act Density 0.008%

    No Known Activations