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

    Neuronpedia

    INDEX
    Explanations

    phrases relating to the extent of something

    oai_token-act-pair · gpt-3.5-turbo

    phrases that quantify the degree or scale of a subject

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Interstitial
    -0.73
    wana
    -0.72
    cair
    -0.71
    verbs
    -0.71
    pton
    -0.69
    reth
    -0.66
    RY
    -0.65
    wark
    -0.65
    stitial
    -0.64
     overheard
    -0.63
    POSITIVE LOGITS
     extent
    0.95
    essment
    0.76
     practicable
    0.74
    conom
    0.71
     amounts
    0.70
    ially
    0.70
    aler
    0.68
    acies
    0.68
    ments
    0.66
    iary
    0.66
    Act Density 0.017%

    No Known Activations