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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing capability and competence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    svp
    -0.17
    fur
    -0.16
    ee
    -0.15
    çĿ£
    -0.15
     Mechanics
    -0.15
    è¸
    -0.15
    ede
    -0.14
    ie
    -0.14
    emoc
    -0.14
    à¤ķन
    -0.14
    POSITIVE LOGITS
     of
    0.20
    -bodied
    0.17
    ule
    0.17
    ippet
    0.16
    cies
    0.15
     enough
    0.15
    (cap
    0.15
    theid
    0.15
     bod
    0.15
    UTO
    0.15
    Act Density 0.008%

    No Known Activations