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

    Neuronpedia

    INDEX
    Explanations

    words or phrases that express numerical values or quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nl
    -0.15
    ("//*[@
    -0.15
    sz
    -0.15
    avity
    -0.14
    hy
    -0.14
    ag
    -0.14
    ukkit
    -0.14
    ɵ
    -0.14
    orna
    -0.14
    resse
    -0.14
    POSITIVE LOGITS
    aku
    0.17
    argins
    0.15
    ebi
    0.15
     olab
    0.15
     京
    0.15
    ledo
    0.14
     terminal
    0.14
    ija
    0.14
    ufe
    0.14
    ako
    0.14
    Act Density 0.022%

    No Known Activations