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

    Neuronpedia

    INDEX
    Explanations

    references to the character Thor and related terms in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    urga
    -0.17
    urf
    -0.16
    cura
    -0.16
    ocracy
    -0.15
    chaft
    -0.14
    ertia
    -0.14
    enda
    -0.14
    ares
    -0.14
    ektor
    -0.14
    ya
    -0.14
    POSITIVE LOGITS
    stan
    0.17
    folio
    0.16
    loff
    0.16
    fol
    0.15
    walk
    0.14
    ÄŁan
    0.14
    ÑĤаÑħ
    0.14
    rier
    0.14
    undles
    0.14
    éĻħ
    0.13
    Act Density 0.020%

    No Known Activations