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

    Neuronpedia

    INDEX
    Explanations

    terms or labels related to technical specifications or requirements

    oai_token-act-pair · gpt-3.5-turbo

    terms related to official or standard protocols and specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xual
    -0.95
    ourke
    -0.81
    hner
    -0.78
    eteenth
    -0.76
    conom
    -0.76
    ossession
    -0.75
    worn
    -0.75
    ":-
    -0.75
    bringing
    -0.74
    SEE
    -0.74
    POSITIVE LOGITS
     versions
    1.22
     implementations
    1.11
     ones
    1.11
     functionality
    1.11
     configuration
    1.09
     API
    1.09
     keywords
    1.08
     version
    1.07
     settings
    1.07
    izations
    1.04
    Act Density 0.309%

    No Known Activations