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

    Neuronpedia

    INDEX
    Explanations

    obvious or straightforward concepts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "obvious."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nan
    -0.93
    ingers
    -0.84
    borg
    -0.80
    psey
    -0.80
    iership
    -0.75
    isol
    -0.73
    aeper
    -0.73
    rams
    -0.72
    rigan
    -0.72
    utherland
    -0.68
    POSITIVE LOGITS
    iary
    0.92
     obvious
    0.79
    holes
    0.74
     signs
    0.71
    LY
    0.71
     flaws
    0.70
     contradiction
    0.70
     omission
    0.69
    hole
    0.69
     Signs
    0.68
    Act Density 0.017%

    No Known Activations