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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and symbols, particularly colons and semicolons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    #
    -0.18
    strict
    -0.15
    .cv
    -0.15
     chy
    -0.14
    mtree
    -0.14
    661
    -0.14
    寸
    -0.14
    modifiable
    -0.14
     Moines
    -0.14
    ivet
    -0.13
    POSITIVE LOGITS
    D
    0.23
    DDD
    0.22
    Ds
    0.19
    roll
    0.16
     Ernst
    0.16
    DD
    0.16
     Coh
    0.15
    uD
    0.15
    .="
    0.15
    P
    0.15
    Act Density 0.020%

    No Known Activations