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

    Neuronpedia

    INDEX
    Explanations

    contractions of "it is" and "it has"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the pronoun "it" and personal pronouns like "I."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Rut
    -0.62
    bold
    -0.61
    ãĥĩãĤ£
    -0.60
    pathic
    -0.59
    ports
    -0.59
     Bord
    -0.59
     Chero
    -0.58
     Aram
    -0.58
     Trad
    -0.58
     Presbyter
    -0.58
    POSITIVE LOGITS
     arrived
    0.76
     toured
    0.70
     arrive
    0.69
     deployed
    0.68
     booked
    0.68
     disbanded
    0.67
    umbnails
    0.67
     resumed
    0.67
     questioned
    0.66
     introduced
    0.66
    Act Density 0.219%

    No Known Activations