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

    Neuronpedia

    INDEX
    Explanations

    symbols and punctuation marks

    oai_token-act-pair · gpt-3.5-turbo

    instances of punctuation marks and special characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oret
    -0.83
    inates
    -0.66
    ona
    -0.65
    nai
    -0.64
    atan
    -0.63
     incent
    -0.61
    Especially
    -0.59
    pring
    -0.58
    itionally
    -0.58
    ilk
    -0.58
    POSITIVE LOGITS
     there
    0.97
     we
    0.88
    there
    0.82
     nobody
    0.80
     it
    0.79
     they
    0.75
     journalists
    0.71
     emerges
    0.68
     commentators
    0.67
     astronomers
    0.67
    Act Density 0.206%

    No Known Activations