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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, specifically periods, indicating the end of statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     prest
    -0.76
    aterasu
    -0.72
    ihilation
    -0.72
    izont
    -0.72
     quickest
    -0.72
     bang
    -0.72
     handy
    -0.71
    ency
    -0.71
     maxim
    -0.70
    isher
    -0.70
    POSITIVE LOGITS
     Recent
    1.21
     Critics
    1.20
     Specifically
    1.19
     Earlier
    1.16
     Recently
    1.13
     Whereas
    1.12
     Particularly
    1.10
     While
    1.08
     Although
    1.07
     Concern
    1.07
    Act Density 0.242%

    No Known Activations