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

    Neuronpedia

    INDEX
    Explanations

    instances of the letter 's' in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IQ
    -0.71
    ERN
    -0.61
    ocaust
    -0.60
     trusts
    -0.59
    aneers
    -0.58
     regimes
    -0.58
     climates
    -0.56
    esp
    -0.56
    attacks
    -0.56
    trust
    -0.56
    POSITIVE LOGITS
    forth
    0.80
     whats
    0.72
     illustrate
    0.68
    omething
    0.67
     excerpt
    0.67
    nesday
    0.63
     brill
    0.63
     hoping
    0.63
    fortunately
    0.63
     Delicious
    0.63
    Act Density 0.018%

    No Known Activations