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

    Neuronpedia

    INDEX
    Explanations

    verb forms relating to the direct object of a sentence

    oai_token-act-pair · gpt-3.5-turbo

    references to "subject" and variations associated with it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ERROR
    -0.79
    AUD
    -0.68
    hetto
    -0.65
    weed
    -0.61
    ereo
    -0.61
    SER
    -0.61
    cia
    -0.59
    ttp
    -0.59
     Sons
    -0.57
    creen
    -0.57
    POSITIVE LOGITS
    ivity
    1.48
    matter
    1.38
    ivities
    1.33
    ivist
    1.33
    ively
    1.32
     matter
    1.23
    ivism
    1.20
    ion
    1.17
    ive
    1.11
     Matter
    1.10
    Act Density 0.022%

    No Known Activations