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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lander
    -0.16
    ixa
    -0.15
    draft
    -0.15
     punt
    -0.14
    ãĤĤãĤĬ
    -0.14
     scrub
    -0.14
     substituted
    -0.14
    iddet
    -0.14
    asan
    -0.13
     기íĥĢ
    -0.13
    POSITIVE LOGITS
     Watts
    0.17
    osaic
    0.15
    782
    0.15
    757
    0.15
    Multiplicity
    0.14
    ump
    0.14
     Salisbury
    0.14
    lisi
    0.14
     Lump
    0.14
     ÎĶε
    0.14
    Act Density 0.049%

    No Known Activations