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

    Neuronpedia

    INDEX
    Explanations

    affirmations and claims relating to the nature or state of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     unthinkable
    -0.14
    orton
    -0.14
     unforgettable
    -0.14
    ouser
    -0.14
    zburg
    -0.14
    nio
    -0.14
    uely
    -0.14
    agr
    -0.14
    inheritDoc
    -0.13
    uers
    -0.13
    POSITIVE LOGITS
     necessary
    0.27
     incumbent
    0.26
     possible
    0.24
    necessary
    0.23
    possible
    0.21
     exped
    0.20
     assumed
    0.20
     essential
    0.19
     wis
    0.18
     hoped
    0.18
    Act Density 0.177%

    No Known Activations