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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to software default settings

    oai_token-act-pair · gpt-3.5-turbo

    references to default settings or configurations in a technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    borough
    -0.90
    wick
    -0.77
    areth
    -0.76
    andan
    -0.72
    chn
    -0.72
    wife
    -0.71
    asus
    -0.69
    atform
    -0.68
    iddles
    -0.68
    nian
    -0.68
    POSITIVE LOGITS
     settings
    0.93
     behaviour
    0.86
     behavior
    0.86
    izable
    0.81
     gateway
    0.80
     disclaimer
    0.80
     mode
    0.75
    dict
    0.74
     configuration
    0.74
    isable
    0.74
    Act Density 0.034%

    No Known Activations