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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating direction or guidance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÙĪاÙĩ
    -0.17
    nds
    -0.16
    artz
    -0.15
    555
    -0.14
    IMIZE
    -0.14
     flip
    -0.13
    át
    -0.13
    озÑı
    -0.13
     tw
    -0.13
    ari
    -0.13
    POSITIVE LOGITS
     track
    0.37
    track
    0.32
    _track
    0.28
     Track
    0.27
    Track
    0.27
     course
    0.26
    -track
    0.26
    .track
    0.24
     tracks
    0.23
     TRACK
    0.22
    Act Density 0.049%

    No Known Activations