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

    Neuronpedia

    INDEX
    Explanations

    phrases starting with "I" and verb phrases detailing personal actions and experiences

    oai_token-act-pair · gpt-3.5-turbo

    statements involving the speaker's thoughts or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hyde
    -0.71
    staking
    -0.68
    ategory
    -0.64
     Poe
    -0.63
    mone
    -0.62
    agos
    -0.62
    assad
    -0.61
    senal
    -0.60
     eleph
    -0.59
     tradem
    -0.59
    POSITIVE LOGITS
    Ĥª
    0.82
    ãĤ»
    0.79
     Learned
    0.75
    iverse
    0.71
    natureconservancy
    0.71
     happened
    0.70
    azes
    0.69
     nutshell
    0.67
     boils
    0.67
    asty
    0.67
    Act Density 0.132%

    No Known Activations