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

    Neuronpedia

    INDEX
    Explanations

    comparative phrases using the term "as"

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express comparisons or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aeda
    -0.75
    OWN
    -0.70
    floor
    -0.67
    INS
    -0.66
    eca
    -0.66
    itatively
    -0.64
    ursday
    -0.64
    oyer
    -0.64
    ITH
    -0.64
    arthy
    -0.63
    POSITIVE LOGITS
    lihood
    0.74
    ricular
    0.66
     initially
    0.63
    semb
    0.63
     critics
    0.62
     doub
    0.60
     doubtless
    0.59
     disagree
    0.59
     Brawl
    0.57
     superf
    0.57
    Act Density 0.061%

    No Known Activations