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

    Neuronpedia

    INDEX
    Explanations

    sentences or phrases that follow a certain punctuation format, specifically full stops (periods)

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ―――――
    -0.66
     VEND
    -0.64
     FetchType
    -0.63
     Hig
    -0.63
    Hig
    -0.62
     løpet
    -0.62
     مشار
    -0.61
     PREG
    -0.61
     Mada
    -0.61
     gts
    -0.60
    POSITIVE LOGITS
    \.
    1.15
    _.
    1.07
    ().
    1.06
    .
    1.05
    +'.
    1.00
    }$.
    0.99
    +".
    0.98
    `.
    0.98
    }.
    0.98
    .$.
    0.97
    Act Density 0.711%

    No Known Activations