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

    Neuronpedia

    INDEX
    Explanations

    moments or events that occur abruptly or unexpectedly

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abel
    -0.16
    chant
    -0.16
    quential
    -0.16
    alsex
    -0.15
    ادا
    -0.15
    fight
    -0.14
    éĢIJ
    -0.14
    alo
    -0.14
    IBE
    -0.14
    ider
    -0.14
    POSITIVE LOGITS
    aneously
    0.27
    aneous
    0.24
    ness
    0.21
    ;y
    0.20
    orks
    0.20
    sworth
    0.19
    630
    0.18
    mente
    0.18
    -death
    0.17
    953
    0.16
    Act Density 0.029%

    No Known Activations