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

    Neuronpedia

    INDEX
    Explanations

    adjectives describing size or importance

    oai_token-act-pair · gpt-3.5-turbo

    descriptors indicating size or significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    obook
    -0.87
    eanor
    -0.79
    rower
    -0.77
    ridor
    -0.75
    plementation
    -0.74
    esthesia
    -0.74
    ynthesis
    -0.74
    alion
    -0.73
    emark
    -0.71
    etry
    -0.71
    POSITIVE LOGITS
     ambassadors
    1.33
     targets
    1.32
     reminders
    1.27
     additions
    1.25
     entities
    1.21
     embodiments
    1.21
     counterparts
    1.21
     replacements
    1.21
     substitutes
    1.20
     performers
    1.19
    Act Density 0.429%

    No Known Activations