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

    Neuronpedia

    INDEX
    Explanations

    punctuation and numeric values within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    phia
    -0.20
    opsy
    -0.16
    737
    -0.16
    swer
    -0.16
    iya
    -0.16
    kowski
    -0.15
    iber
    -0.15
    705
    -0.15
     CommandType
    -0.14
    oom
    -0.14
    POSITIVE LOGITS
     Britt
    0.16
     resett
    0.16
    ì§Ģ
    0.15
    CP
    0.15
    ÅĽcie
    0.15
    Walk
    0.15
     Pell
    0.15
    ष
    0.14
     Walk
    0.14
     åŃ
    0.14
    Act Density 0.028%

    No Known Activations