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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks

    oai_token-act-pair · gpt-3.5-turbo

    repeated phrases or statements indicating negation or contradiction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gypt
    -0.74
     feasibility
    -0.66
    ounded
    -0.65
     chains
    -0.64
     tro
    -0.62
     herds
    -0.61
     bount
    -0.59
     bounty
    -0.58
    mud
    -0.58
     trave
    -0.56
    POSITIVE LOGITS
     sir
    0.94
     whatsoever
    0.87
     except
    0.79
     nor
    0.78
     thank
    0.76
    onsense
    0.71
     uh
    0.70
     please
    0.68
    Shift
    0.67
     Mistress
    0.67
    Act Density 0.056%

    No Known Activations