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

    Neuronpedia

    INDEX
    Explanations

    phrases and expressions related to duration or persistence over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bor
    -0.15
    acher
    -0.14
    anson
    -0.14
    è¡
    -0.14
    least
    -0.14
    anik
    -0.14
     almost
    -0.13
    iest
    -0.13
    vio
    -0.13
    ross
    -0.13
    POSITIVE LOGITS
     long
    0.40
     very
    0.32
     too
    0.31
     TOO
    0.28
     much
    0.27
    long
    0.27
     many
    0.27
     muito
    0.26
    very
    0.26
    too
    0.26
    Act Density 0.084%

    No Known Activations