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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks used in lists or series

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    angu
    -0.74
    ikawa
    -0.71
    laughter
    -0.68
    untarily
    -0.67
    sburg
    -0.67
    vale
    -0.66
    tsy
    -0.65
    phant
    -0.64
    ãĤ¢ãĥ«
    -0.63
    animate
    -0.63
    POSITIVE LOGITS
     however
    1.30
     meanwhile
    1.22
     moreover
    1.14
     consisting
    0.98
     comprising
    0.98
     incidentally
    0.98
     dubbed
    0.97
     nicknamed
    0.95
     which
    0.94
     spearheaded
    0.93
    Act Density 0.101%

    No Known Activations