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

    Neuronpedia

    INDEX
    Explanations

    words related to analysis and comparison, particularly in research contexts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to statistical analysis and calculations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pal
    -0.78
    ihu
    -0.76
    jew
    -0.76
    krit
    -0.72
    redo
    -0.71
    agar
    -0.71
    arah
    -0.70
    oug
    -0.70
    lv
    -0.69
    inery
    -0.69
    POSITIVE LOGITS
     various
    1.45
     different
    1.40
     each
    1.29
     respective
    1.15
     specific
    1.04
     varying
    1.03
     particular
    0.99
     differing
    0.99
     Different
    0.97
     individual
    0.95
    Act Density 0.476%

    No Known Activations