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

    Neuronpedia

    INDEX
    Explanations

    adjectives and phrases that describe characteristics or qualities of various subjects

    oai_token-act-pair · gpt-3.5-turbo

    phrases that describe qualities or characteristics of a subject

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Alive
    -0.61
     WATCHED
    -0.60
    ————
    -0.58
    Bus
    -0.58
    shoot
    -0.58
    umbn
    -0.57
    urch
    -0.55
    addon
    -0.55
    NAS
    -0.54
    wheel
    -0.54
    POSITIVE LOGITS
     justifies
    1.31
     prevents
    1.28
     allows
    1.27
     exceeds
    1.25
     enables
    1.23
     enhances
    1.22
     resembles
    1.21
     distinguishes
    1.20
     ensures
    1.20
     makes
    1.18
    Act Density 0.137%

    No Known Activations