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

    Neuronpedia

    INDEX
    Explanations

    keywords related to making decisions or judgments based on certain criteria

    oai_token-act-pair · gpt-3.5-turbo

    phrases that involve making decisions or conclusions based on certain criteria or information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    shr
    -0.82
    osen
    -0.76
    nel
    -0.75
    ESE
    -0.72
     Leilan
    -0.70
    fruit
    -0.70
    dra
    -0.70
    antha
    -0.69
     Donovan
    -0.69
    icz
    -0.68
    POSITIVE LOGITS
     upon
    0.77
     loosely
    0.75
    tesy
    0.70
    awaru
    0.70
     solely
    0.68
     paycheck
    0.68
    uity
    0.67
    edience
    0.67
    monary
    0.67
     veter
    0.67
    Act Density 0.029%

    No Known Activations