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

    Neuronpedia

    INDEX
    Explanations

    Scandinavian characters, likely from a specific language

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of a specific character or symbol in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agonist
    -0.85
    iple
    -0.75
    idepress
    -0.73
    iazep
    -0.69
    aneously
    -0.67
    cler
    -0.65
     Hera
    -0.65
    ogene
    -0.63
    ciating
    -0.63
     kernels
    -0.62
    POSITIVE LOGITS
    å
    1.07
    sson
    0.88
    ĺ
    0.88
    ¢
    0.86
    ø
    0.84
    µ
    0.82
    ·
    0.81
    ´
    0.79
    sb
    0.78
    ð
    0.78
    Act Density 0.007%

    No Known Activations