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

    Neuronpedia

    INDEX
    Explanations

    the adverb "usually" and its contextual variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ublic
    -0.61
    qed
    -0.59
     ней
    -0.58
     braccia
    -0.57
     Zachary
    -0.56
    QED
    -0.56
     zostało
    -0.56
     Text
    -0.55
     sprá
    -0.55
    !("{
    -0.54
    POSITIVE LOGITS
     usually
    1.47
     Usually
    1.40
    Usually
    1.40
     normally
    1.31
    Typically
    1.30
     Typically
    1.30
    usually
    1.28
     Normally
    1.28
    normally
    1.25
     typically
    1.24
    Act Density 0.163%

    No Known Activations