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

    Neuronpedia

    INDEX
    Explanations

    special characters and computer programming language syntax

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, specifically commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    natureconservancy
    -0.73
    interstitial
    -0.71
     exha
    -0.70
    conom
    -0.69
     unnecess
    -0.69
    uggest
    -0.67
     perspect
    -0.67
     footing
    -0.66
     behavi
    -0.66
     corrid
    -0.66
    POSITIVE LOGITS
     etc
    1.05
     huh
    0.95
     eh
    0.85
     however
    0.82
     supra
    0.79
     please
    0.78
     aka
    0.76
     et
    0.74
    )"
    0.74
    032
    0.73
    Act Density 1.525%

    No Known Activations