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

    Neuronpedia

    INDEX
    Explanations

    phrases related to direct eye contact

    oai_token-act-pair · gpt-3.5-turbo

    the word "the" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arians
    -0.73
    olicy
    -0.71
    fn
    -0.70
    Reason
    -0.67
    ulner
    -0.65
    mania
    -0.65
    ional
    -0.65
    soever
    -0.64
    Topics
    -0.63
    acca
    -0.62
    POSITIVE LOGITS
     midst
    1.55
     vicinity
    1.20
     meantime
    1.18
     aftermath
    1.09
     guise
    1.07
     middle
    1.04
     same
    1.03
     context
    1.02
     slightest
    0.98
     wake
    0.95
    Act Density 0.355%

    No Known Activations