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

    Neuronpedia

    INDEX
    Explanations

    terms related to assessments and evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ø©
    -0.16
    ç±į
    -0.15
    ief
    -0.15
    ality
    -0.15
    gow
    -0.15
    etic
    -0.15
    thrown
    -0.14
    nero
    -0.14
     ******************************************************************************/↵
    -0.14
    Č↵
    -0.14
    POSITIVE LOGITS
    uated
    0.33
    ution
    0.24
    uations
    0.21
    uable
    0.20
    uating
    0.19
    uator
    0.18
    shi
    0.17
    utors
    0.17
    uta
    0.17
    utar
    0.16
    Act Density 0.025%

    No Known Activations