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

    Neuronpedia

    INDEX
    Explanations

    action verbs in the past tense

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "read" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pora
    -0.63
    uve
    -0.61
    vre
    -0.60
     Circle
    -0.58
    astern
    -0.56
     degree
    -0.55
    ño
    -0.54
     Territory
    -0.52
     sphere
    -0.52
     Belg
    -0.52
    POSITIVE LOGITS
     aloud
    1.32
    \\\\\\\\
    0.95
    just
    0.88
    ahead
    0.86
    dress
    0.84
    printed
    0.83
    write
    0.80
     omin
    0.79
    written
    0.79
    ILY
    0.78
    Act Density 0.023%

    No Known Activations