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

    Neuronpedia

    INDEX
    Explanations

    strings that resemble technical identifiers or codes

    oai_token-act-pair · gpt-3.5-turbo

    structured data and identifiers, particularly related to numbers and classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ritch
    -0.84
    bush
    -0.83
    atan
    -0.83
    issance
    -0.83
    sonian
    -0.79
    pless
    -0.79
    imar
    -0.79
    uce
    -0.76
    ersive
    -0.75
    achev
    -0.74
    POSITIVE LOGITS
     redacted
    0.77
     Description
    0.76
     annotation
    0.71
    Mine
    0.71
    coded
    0.70
     informant
    0.69
     numbering
    0.68
     registration
    0.67
     NAME
    0.66
     tag
    0.66
    Act Density 0.275%

    No Known Activations