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

    Neuronpedia

    INDEX
    Explanations

    opinion pieces and editorials

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "op-ed" and related forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    artifacts
    -0.72
    displayText
    -0.72
    bang
    -0.67
    SPONSORED
    -0.67
    ubi
    -0.64
    absolute
    -0.64
     Magicka
    -0.64
     Knock
    -0.63
     pies
    -0.62
    prototype
    -0.62
    POSITIVE LOGITS
    ruary
    0.76
    OPLE
    0.75
    insula
    0.74
    ias
    0.74
    orial
    0.71
    ipel
    0.71
    itors
    0.69
    umn
    0.69
    lee
    0.67
    DonaldTrump
    0.66
    Act Density 0.020%

    No Known Activations