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

    Neuronpedia

    INDEX
    Explanations

    verbs related to physical actions involving pushing out or removing something

    oai_token-act-pair · gpt-3.5-turbo

    references to the action of flushing or related processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yers
    -0.74
    anwhile
    -0.70
    ourke
    -0.68
    ean
    -0.64
     lawy
    -0.64
    ordan
    -0.63
    unes
    -0.62
    */(
    -0.61
    ãģķ
    -0.61
    ramer
    -0.61
    POSITIVE LOGITS
     flush
    1.37
     flushed
    1.11
     toilets
    0.82
    ishable
    0.77
    idious
    0.74
    flush
    0.74
    uates
    0.74
    uation
    0.72
    ishes
    0.71
    itus
    0.70
    Act Density 0.008%

    No Known Activations