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

    Neuronpedia

    INDEX
    Explanations

    questions about various aspects of a topic or situation

    oai_token-act-pair · gpt-3.5-turbo

    questions about the roles, desires, and conditions of people and entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IFIED
    -0.74
    ocaust
    -0.72
    hyde
    -0.64
    idon
    -0.62
     Mushroom
    -0.60
    rome
    -0.60
    OV
    -0.60
    hig
    -0.59
    wana
    -0.59
    POR
    -0.58
    POSITIVE LOGITS
    soever
    1.35
     they
    1.01
     accordingly
    0.93
     thereof
    0.91
    abouts
    0.91
     consequ
    0.86
     it
    0.81
     obstacles
    0.79
     THEY
    0.79
     importantly
    0.78
    Act Density 0.101%

    No Known Activations