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

    Neuronpedia

    INDEX
    Explanations

    specific pronouns and verbs referring to actions performed by individuals

    oai_token-act-pair · gpt-3.5-turbo

    the use of personal pronouns and phrases indicating individual experiences or feelings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Enlarge
    -1.22
    '>
    -0.86
    toggle
    -0.80
    Yeah
    -0.78
    -'
    -0.76
    't
    -0.73
    Flickr
    -0.73
    Exit
    -0.73
    '/
    -0.73
    '-
    -0.72
    POSITIVE LOGITS
     cannot
    1.28
     will
    0.87
     cant
    0.81
     must
    0.81
     is
    0.80
     may
    0.79
     learnt
    0.78
     would
    0.74
     are
    0.74
     can
    0.73
    Act Density 0.628%

    No Known Activations