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

    Neuronpedia

    INDEX
    Explanations

    words related to assumptions or presumption in statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    essler
    -0.21
    ness
    -0.18
    lops
    -0.16
    zeug
    -0.15
    esian
    -0.15
    ened
    -0.15
    elsey
    -0.15
    \grid
    -0.15
    lle
    -0.15
    essen
    -0.15
    POSITIVE LOGITS
    ably
    0.19
    ively
    0.19
    ptions
    0.18
     Assumes
    0.17
     rằng
    0.16
    /assert
    0.15
    ,nonatomic
    0.15
    assume
    0.15
    ODO
    0.15
     assumes
    0.15
    Act Density 0.035%

    No Known Activations