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

    Neuronpedia

    INDEX
    Explanations

    references to the word "off" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    apur
    -0.15
    ittel
    -0.15
    ih
    -0.14
    heed
    -0.14
    fires
    -0.14
    åĿĤ
    -0.14
    ãĥ¼ãĥĢ
    -0.14
    pective
    -0.14
    ãģĤãĤĬãģĮãģ¨ãģĨ
    -0.13
    .Struct
    -0.13
    POSITIVE LOGITS
    ensively
    0.31
    shoot
    0.20
    loaded
    0.19
    beat
    0.19
     beaten
    0.17
    ensive
    0.17
    ·»
    0.16
    ertoire
    0.16
    ically
    0.15
    hand
    0.15
    Act Density 0.026%

    No Known Activations