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

    Neuronpedia

    INDEX
    Explanations

    expressions related to paths and navigation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bek
    -0.15
    enburg
    -0.15
    åªĴ
    -0.15
    737
    -0.14
     midnight
    -0.14
     precis
    -0.13
     etc
    -0.13
     place
    -0.13
    allback
    -0.13
     Thur
    -0.13
    POSITIVE LOGITS
     past
    0.21
    past
    0.21
     soon
    0.19
    soon
    0.18
    skirts
    0.18
    foy
    0.17
     Soon
    0.17
     Past
    0.17
    Soon
    0.16
    unsch
    0.16
    Act Density 0.021%

    No Known Activations