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

    Neuronpedia

    INDEX
    Explanations

    words related to events reaching a significant point or conclusion

    oai_token-act-pair · gpt-3.5-turbo

    terms related to outcomes or climaxes of events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Neighbor
    -0.80
    aky
    -0.77
    vag
    -0.74
    bel
    -0.72
    uns
    -0.72
    pel
    -0.69
    nery
    -0.68
    alcohol
    -0.66
    guy
    -0.66
    away
    -0.66
    POSITIVE LOGITS
     culminating
    1.11
     culmin
    0.98
     culmination
    0.98
     culminated
    0.95
     climax
    0.84
    SourceFile
    0.79
     tert
    0.73
    ESCO
    0.70
     fruition
    0.70
    ãĤ¤ãĥĪ
    0.68
    Act Density 0.018%

    No Known Activations