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

    Neuronpedia

    INDEX
    Explanations

    commands or instructions starting with "Don't."

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "don't."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ħĭ
    -0.86
    £ı
    -0.82
    ĪĴ
    -0.77
     behavi
    -0.76
     Reloaded
    -0.75
    Reviewer
    -0.75
     ingred
    -0.73
     shorth
    -0.70
    milo
    -0.68
     ancest
    -0.67
    POSITIVE LOGITS
    cha
    0.89
     bother
    0.87
    osaurs
    0.84
    ables
    0.83
    rave
    0.82
    ween
    0.81
    ardless
    0.81
    ional
    0.81
    reprene
    0.80
    urb
    0.79
    Act Density 0.055%

    No Known Activations