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

    Neuronpedia

    INDEX
    Explanations

    phrases related to technical instructions or explanations

    oai_token-act-pair · gpt-3.5-turbo

    inquiries about understanding concepts or ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    leased
    -0.86
    ospons
    -0.81
    zbollah
    -0.74
     vacated
    -0.72
    ilyn
    -0.72
    urther
    -0.72
     renewed
    -0.71
    atform
    -0.70
    vertisement
    -0.70
     Vengeance
    -0.70
    POSITIVE LOGITS
     jargon
    1.40
     mathematic
    1.28
     diagrams
    1.25
     maths
    1.23
     math
    1.23
     intuitive
    1.22
     equations
    1.21
     decipher
    1.20
     algebra
    1.18
     mathemat
    1.18
    Act Density 0.748%

    No Known Activations