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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and symbols indicating structure or emphasis in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .bundle
    -0.15
    ãĥ«ãĥķ
    -0.14
     داخ
    -0.14
    decorators
    -0.14
     Sexo
    -0.14
    704
    -0.14
     COPYING
    -0.14
    leurs
    -0.14
    hire
    -0.13
    SKTOP
    -0.13
    POSITIVE LOGITS
    ECTOR
    0.15
     Lime
    0.14
    znik
    0.14
     damp
    0.14
     foreign
    0.14
    alus
    0.14
    bourg
    0.14
    estic
    0.14
     Lim
    0.14
     cum
    0.13
    Act Density 0.008%

    No Known Activations