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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating addition or continuation in a sentence

    oai_token-act-pair · gpt-3.5-turbo

    instances of reported speech or citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    peg
    -0.79
    tes
    -0.67
    unker
    -0.66
    orce
    -0.64
     Stronghold
    -0.63
    cus
    -0.63
    uddy
    -0.59
    pires
    -0.59
    course
    -0.59
    û
    -0.57
    POSITIVE LOGITS
    apest
    0.69
    uations
    0.67
     sarc
    0.63
     sarcast
    0.63
     [+
    0.62
     iT
    0.62
     quoting
    0.61
    amera
    0.60
    BUS
    0.60
    ribune
    0.59
    Act Density 0.081%

    No Known Activations