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

    Neuronpedia

    INDEX
    Explanations

    terms related to interruptions and disturbances in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iras
    -0.14
    lia
    -0.14
    رض
    -0.14
    borg
    -0.14
    haul
    -0.14
    irting
    -0.13
    709
    -0.13
     republika
    -0.13
    itone
    -0.13
    anes
    -0.13
    POSITIVE LOGITS
    /dist
    0.17
    ä¸įäºĨ
    0.15
     heck
    0.14
     anno
    0.14
     hell
    0.13
    _asm
    0.13
     Chain
    0.13
    ible
    0.13
    _ASM
    0.13
    olare
    0.13
    Act Density 0.052%

    No Known Activations