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

    Neuronpedia

    INDEX
    Explanations

    adjectives related to extreme or high intensity

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with enduring or repeated actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     toget
    -0.66
    FactoryReloaded
    -0.60
    fax
    -0.60
    hift
    -0.59
    step
    -0.57
    SIZE
    -0.57
     NCT
    -0.57
    fram
    -0.57
    creen
    -0.56
    CHR
    -0.56
    POSITIVE LOGITS
    ant
    2.76
    ance
    2.61
    ants
    2.37
    antly
    2.34
    ancy
    2.31
    ances
    2.30
    ANCE
    1.99
    ancies
    1.92
    ANT
    1.91
    antes
    1.87
    Act Density 0.153%

    No Known Activations