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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "on" and its contextual relevance in various phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    formace
    -0.15
    oba
    -0.15
    andes
    -0.15
    веÑģÑĤи
    -0.15
    омеÑĢ
    -0.14
    OUCH
    -0.14
    htdocs
    -0.14
    anton
    -0.14
    über
    -0.13
    anness
    -0.13
    POSITIVE LOGITS
     track
    0.40
     target
    0.35
     course
    0.35
     pace
    0.31
    track
    0.28
    target
    0.27
     schedule
    0.26
    -target
    0.26
     tract
    0.26
     Course
    0.25
    Act Density 0.047%

    No Known Activations