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

    Neuronpedia

    INDEX
    Explanations

    instances of dialogue and expressions of character interactions in storytelling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     дÑĢÑĥго
    -0.15
    edor
    -0.14
    ertz
    -0.14
    IRON
    -0.14
    raud
    -0.13
    efon
    -0.13
    iron
    -0.13
    Ã
    -0.13
     Cheat
    -0.13
    ucson
    -0.13
    POSITIVE LOGITS
     about
    0.17
     how
    0.16
     describe
    0.16
     statistics
    0.16
     describing
    0.15
     why
    0.15
     talk
    0.15
    .about
    0.15
     statist
    0.15
     list
    0.15
    Act Density 0.245%

    No Known Activations