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

    Neuronpedia

    INDEX
    Explanations

    phrases related to normalcy and typical behavior

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    audiovisuel
    -0.65
    arXiv
    -0.55
     linkovi
    -0.55
    PerformLayout
    -0.51
     todav
    -0.51
    pannt
    -0.51
    ̀n
    -0.50
    makeConstraints
    -0.50
    ConstraintMaker
    -0.50
    UnsafeEnabled
    -0.49
    POSITIVE LOGITS
     Normally
    1.25
     normally
    1.21
    Normally
    1.18
     habituellement
    1.18
     usual
    1.15
    normally
    1.13
    Usual
    1.09
     Usually
    1.09
     usually
    1.08
    usual
    1.06
    Act Density 0.226%

    No Known Activations