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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "literally" and related phrases about reality or truth

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Malley
    -0.51
     ivelany
    -0.47
    adaptiveStyles
    -0.47
    ESOME
    -0.45
     typelib
    -0.45
     дописавши
    -0.44
     ...]
    -0.44
     الرياضيه
    -0.42
    دانشنامهٔ
    -0.41
    -0.41
    POSITIVE LOGITS
     literally
    1.59
    Literally
    1.52
     Literally
    1.49
     literalmente
    1.47
     literal
    1.45
    literally
    1.41
     Literal
    1.14
    literal
    1.13
    Literal
    1.03
     LITER
    1.01
    Act Density 0.136%

    No Known Activations