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

    Neuronpedia

    INDEX
    Explanations

    intervals and values associated with mathematical concepts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to statistical intervals and probability distributions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lander
    -0.74
    hatt
    -0.73
    husband
    -0.72
    clad
    -0.71
     Franch
    -0.70
    advertising
    -0.68
    amed
    -0.67
     Statue
    -0.67
    justice
    -0.66
    Land
    -0.65
    POSITIVE LOGITS
     interval
    3.73
     intervals
    3.70
     increments
    1.38
     intermediate
    1.21
     elapsed
    1.08
     interpol
    1.05
     periodic
    1.03
     duration
    1.02
     intermedi
    1.01
     intermittent
    0.99
    Act Density 0.015%

    No Known Activations