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

    Neuronpedia

    INDEX
    Explanations

    the adverb "literally" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     enfans
    -0.78
    ambién
    -0.74
    ientras
    -0.70
     miniaturka
    -0.68
     Infór
    -0.68
     avoient
    -0.66
     soñar
    -0.66
     valentín
    -0.65
     Grüsse
    -0.63
     soñ
    -0.63
    POSITIVE LOGITS
     evaluation
    0.57
     Rat
    0.51
     Exhibition
    0.48
     rat
    0.48
     Evaluation
    0.48
    act
    0.46
     PLA
    0.45
     act
    0.45
     PU
    0.45
    Rat
    0.44
    Act Density 0.212%

    No Known Activations