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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating progress or alignment towards goals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    formace
    -0.15
    anches
    -0.14
     beg
    -0.14
    obus
    -0.14
    andes
    -0.14
    apia
    -0.14
    oba
    -0.14
    æĻ¨
    -0.14
    oucher
    -0.13
    веÑģÑĤи
    -0.13
    POSITIVE LOGITS
     track
    0.36
     target
    0.31
     course
    0.30
    track
    0.28
     tract
    0.27
     schedule
    0.27
     pace
    0.26
    -track
    0.25
    target
    0.24
     Track
    0.24
    Act Density 0.050%

    No Known Activations