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

    Neuronpedia

    INDEX
    Explanations

    phrases related to interruptions and disruptions in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anes
    -0.16
    borg
    -0.15
    iras
    -0.14
    irting
    -0.14
    itung
    -0.13
    haul
    -0.13
    emu
    -0.13
    iscal
    -0.13
    raft
    -0.13
    ennen
    -0.13
    POSITIVE LOGITS
    /dist
    0.18
    ä¸įäºĨ
    0.17
     anno
    0.14
    ÅĻik
    0.14
    514
    0.14
    741
    0.14
    ìĦľëĬĶ
    0.14
    ible
    0.14
    nce
    0.14
    ety
    0.13
    Act Density 0.052%

    No Known Activations