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

    Neuronpedia

    INDEX
    Explanations

    instances of names, particularly "Steph" or variations thereof

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Steph" or variations thereof

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Pengu
    -1.06
     Loans
    -0.84
    querque
    -0.82
    ciating
    -0.80
    20439
    -0.79
     opio
    -0.79
     concess
    -0.78
    ãĥĩãĤ£
    -0.78
     redes
    -0.75
    fell
    -0.72
    POSITIVE LOGITS
    agne
    0.86
    avage
    0.82
    Ãł
    0.80
    agos
    0.77
    ano
    0.77
    ane
    0.76
    inct
    0.70
    aign
    0.70
    erity
    0.69
    oute
    0.68
    Act Density 0.026%

    No Known Activations