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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to networking and technology

    oai_token-act-pair · gpt-3.5-turbo

    technical specifications and model identifiers related to electronic devices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    opian
    -0.71
     passions
    -0.71
     literacy
    -0.69
    iotics
    -0.68
     wiser
    -0.68
     passionate
    -0.67
     passion
    -0.65
    istry
    -0.64
     innocence
    -0.64
    lings
    -0.64
    POSITIVE LOGITS
    001
    1.01
    0001
    0.99
    002
    0.96
    BG
    0.95
    01
    0.94
    003
    0.93
    0100
    0.93
    FG
    0.92
    FH
    0.92
    010
    0.91
    Act Density 0.148%

    No Known Activations