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

    Neuronpedia

    INDEX
    Explanations

    phrases related to utilizing or controlling energy or power

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kup
    -0.17
    ovah
    -0.15
    iability
    -0.15
    ahat
    -0.15
    åºĬ
    -0.15
    jual
    -0.14
    ocrin
    -0.14
    оÑĤÑĢеб
    -0.14
    zee
    -0.14
    arget
    -0.14
    POSITIVE LOGITS
    anas
    0.15
    358
    0.15
    power
    0.14
    ril
    0.14
    arness
    0.14
     Cath
    0.14
    NAS
    0.14
     Fen
    0.14
    aged
    0.13
    illos
    0.13
    Act Density 0.011%

    No Known Activations