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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "correct" and related terms indicating accuracy or truthfulness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    holder
    -0.19
    ISTIC
    -0.17
    klady
    -0.17
    -0.17
    istic
    -0.16
    ittings
    -0.16
    holders
    -0.16
    getic
    -0.16
    jective
    -0.16
    ITY
    -0.15
    POSITIVE LOGITS
    ively
    0.66
    ive
    0.49
    ors
    0.46
    iveness
    0.44
    ives
    0.43
    ivity
    0.40
    ual
    0.35
    ible
    0.33
    eur
    0.33
    ually
    0.32
    Act Density 0.155%

    No Known Activations