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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their associated frequency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãi
    -0.17
    eyse
    -0.15
    urr
    -0.14
    eca
    -0.14
    avras
    -0.13
    «ĺ
    -0.13
    oftware
    -0.13
    Brains
    -0.13
    avior
    -0.12
    yses
    -0.12
    POSITIVE LOGITS
     there
    0.26
     indeed
    0.24
     after
    0.20
     Indeed
    0.20
    there
    0.19
     hence
    0.19
     they
    0.19
     it
    0.19
     during
    0.19
     this
    0.19
    Act Density 0.110%

    No Known Activations