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

    Neuronpedia

    INDEX
    Explanations

    terms or phrases related to comparison or evaluation based on specific criteria

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express comparisons or analyses related to specific concepts or topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cosponsors
    -0.89
    idel
    -0.89
    fort
    -0.80
    jad
    -0.80
    atan
    -0.78
    sup
    -0.75
    ©¶æ¥µ
    -0.75
    bay
    -0.75
    icer
    -0.74
    hid
    -0.74
    POSITIVE LOGITS
     sheer
    1.18
     aesthetics
    1.01
     usefulness
    0.95
     longevity
    0.95
     firepower
    0.95
     convenience
    0.95
     quality
    0.95
     demographics
    0.94
     visuals
    0.94
     sophistication
    0.93
    Act Density 0.072%

    No Known Activations