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

    Neuronpedia

    INDEX
    Explanations

    mentions and discussions of strength and conditioning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ohn
    -0.17
    sexual
    -0.15
    ism
    -0.15
    ation
    -0.15
    latin
    -0.15
    als
    -0.15
    ub
    -0.15
     tricks
    -0.14
    arat
    -0.14
    pace
    -0.14
    POSITIVE LOGITS
    holds
    0.26
     Weak
    0.24
     weakness
    0.24
    weak
    0.23
     weak
    0.23
    _weak
    0.21
     weaker
    0.21
    Weak
    0.21
    -strong
    0.21
    /we
    0.20
    Act Density 0.037%

    No Known Activations