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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their respective contextual usage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ija
    -0.14
    ĸī
    -0.14
    ipop
    -0.14
    vik
    -0.14
     Lazy
    -0.14
    BaseContext
    -0.14
    lette
    -0.14
    opi
    -0.13
     Scalars
    -0.13
    ux
    -0.13
    POSITIVE LOGITS
     there
    0.20
     There
    0.17
     nobody
    0.16
    there
    0.15
     no
    0.14
    dit
    0.14
    dings
    0.14
    There
    0.14
    anner
    0.14
    immel
    0.14
    Act Density 0.113%

    No Known Activations