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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate duration or permanence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     intermittent
    -0.15
    ither
    -0.15
    ÑĥÑħ
    -0.15
    ofi
    -0.14
    ast
    -0.14
    acom
    -0.14
    als
    -0.14
    /
    -0.13
    161
    -0.13
     Rapids
    -0.13
    POSITIVE LOGITS
     longer
    0.29
     Longer
    0.28
    ingly
    0.21
     longest
    0.21
    leen
    0.17
    ãģ¡ãģ¯
    0.17
     forever
    0.16
    YLON
    0.16
    arrera
    0.16
    arella
    0.15
    Act Density 0.015%

    No Known Activations