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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the basis or reasoning for decisions or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     basics
    -0.15
     actionTypes
    -0.15
    oval
    -0.14
    973
    -0.14
    eyn
    -0.14
    neum
    -0.14
    over
    -0.14
    uts
    -0.14
     bás
    -0.14
     bravery
    -0.13
    POSITIVE LOGITS
     upon
    0.37
    upon
    0.30
     Upon
    0.28
    Upon
    0.25
     off
    0.20
     solely
    0.18
     Sole
    0.17
     around
    0.17
    camp
    0.16
     loosely
    0.16
    Act Density 0.026%

    No Known Activations