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

    Neuronpedia

    INDEX
    Explanations

    negations or expressions of contrary statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IsEmpty
    -0.59
    .
    -0.57
     corresponden
    -0.53
     is
    -0.53
    sqcup
    -0.53
    ishy
    -0.51
     Silverman
    -0.51
     Dillon
    -0.51
    es
    -0.50
    pretation
    -0.50
    POSITIVE LOGITS
     not
    1.46
    Not
    1.29
     Not
    1.28
    not
    1.25
     NOT
    1.13
     Италијани
    1.07
    IntoConstraints
    1.06
    NOT
    1.04
     Niet
    1.01
     propOrder
    1.00
    Act Density 0.155%

    No Known Activations