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

    Neuronpedia

    INDEX
    Explanations

    parts of words containing the sequence "Pl" followed by a single character

    oai_token-act-pair · gpt-3.5-turbo

    the word "Pl" followed by the number 2, likely referencing a specific term or concept

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    âĸ¬âĸ¬
    -0.81
    âĸ¬
    -0.77
    worthiness
    -0.74
    ãģ®éŃĶ
    -0.69
     Logged
    -0.66
    NESS
    -0.63
    gerald
    -0.63
    ãĥĨãĤ£
    -0.62
    liness
    -0.61
     FANTASY
    -0.60
    POSITIVE LOGITS
    utonium
    1.38
    umbing
    1.34
    atoon
    1.33
    ausible
    1.31
    acement
    1.30
    asma
    1.27
    umb
    1.24
    acid
    1.23
    atter
    1.18
    ummer
    1.16
    Act Density 0.020%

    No Known Activations