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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "far"

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate progress or the state of things over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pron
    -0.67
     EntityItem
    -0.61
    vec
    -0.61
    CLOSE
    -0.59
     fold
    -0.58
     CODE
    -0.57
     Caf
    -0.54
     murd
    -0.53
     constants
    -0.53
    adobe
    -0.52
    POSITIVE LOGITS
     unsuccessful
    0.74
    ounding
    0.68
    ounds
    0.65
    ogo
    0.62
     untouched
    0.61
     hasn
    0.60
     anyway
    0.60
    interstitial
    0.59
     MIA
    0.59
    uko
    0.59
    Act Density 0.045%

    No Known Activations