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

    Neuronpedia

    INDEX
    Explanations

    references to physical strength and its various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    asca
    -0.20
    OGLE
    -0.16
    ingen
    -0.15
    otts
    -0.15
    ary
    -0.15
    ikan
    -0.15
    bage
    -0.15
    ê
    -0.15
    /xhtml
    -0.15
    quin
    -0.14
    POSITIVE LOGITS
    ening
    0.27
    ened
    0.25
    ens
    0.24
    ener
    0.24
    holds
    0.23
    ning
    0.22
    /power
    0.21
    /we
    0.20
    eners
    0.19
     weakness
    0.19
    Act Density 0.024%

    No Known Activations