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

    Neuronpedia

    INDEX
    Explanations

    phrases related to unlimited or unrestricted movement or access

    oai_token-act-pair · gpt-3.5-turbo

    references to flexibility or freedom in location and choices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Interstitial
    -0.68
    Spoiler
    -0.67
    alus
    -0.67
    ItemTracker
    -0.66
    interstitial
    -0.65
    qus
    -0.64
    bda
    -0.63
    orically
    -0.61
    ounded
    -0.61
    ror
    -0.59
    POSITIVE LOGITS
     imaginable
    1.63
     anytime
    1.14
     anywhere
    1.02
     conceivable
    1.01
     whatsoever
    0.91
    soever
    0.86
     regardless
    0.83
     anybody
    0.79
    any
    0.78
    THING
    0.74
    Act Density 0.154%

    No Known Activations