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

    Neuronpedia

    INDEX
    Explanations

    adjectives or verbs related to rapid action or change

    oai_token-act-pair · gpt-3.5-turbo

    significant terms related to urgency and notable occurrences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cffff
    -0.50
    natureconservancy
    -0.46
    çīĪ
    -0.46
    AFP
    -0.43
    MRI
    -0.41
    ool
    -0.40
    izoph
    -0.40
    Phones
    -0.40
    etheless
    -0.40
    _>
    -0.38
    POSITIVE LOGITS
     to
    1.29
    to
    1.08
     TO
    0.93
     unto
    0.90
    To
    0.87
     To
    0.82
     thereto
    0.75
     towards
    0.74
     ta
    0.71
    TO
    0.68
    Act Density 0.834%

    No Known Activations