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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly parentheses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rowse
    -0.18
     bed
    -0.15
     p
    -0.15
    anda
    -0.15
    kes
    -0.15
     Braun
    -0.14
    kou
    -0.14
     Urban
    -0.14
    Ì
    -0.14
     Bed
    -0.14
    POSITIVE LOGITS
    طار
    0.17
    bserv
    0.16
    ncmp
    0.15
     наÑĤÑĥ
    0.15
    BuilderInterface
    0.15
    .scalablytyped
    0.15
    mdir
    0.15
    ëĵĿ
    0.15
    ëĭ¥
    0.14
    UTERS
    0.14
    Act Density 0.005%

    No Known Activations