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

    Neuronpedia

    INDEX
    Explanations

    phrases related to warnings or cautions about future events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atar
    -0.15
    ello
    -0.15
    ammer
    -0.15
     NOT
    -0.15
    a
    -0.15
    ian
    -0.15
    c
    -0.15
    nd
    -0.14
    ediator
    -0.14
    ador
    -0.14
    POSITIVE LOGITS
    egal
    0.15
    ût
    0.15
    žit
    0.15
    OnError
    0.15
    ernet
    0.14
    äng
    0.14
    868
    0.14
    ãĤĵ
    0.14
    /out
    0.14
    StrictEqual
    0.14
    Act Density 0.017%

    No Known Activations