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

    Neuronpedia

    INDEX
    Explanations

    people who speak multiple languages and terms related to language interpretation

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "speaks" and related expressions indicating communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ascade
    -0.72
    neum
    -0.66
    ihara
    -0.65
    aven
    -0.65
     Rockies
    -0.64
    insk
    -0.62
    ledge
    -0.61
    Van
    -0.61
    awn
    -0.60
    avior
    -0.60
    POSITIVE LOGITS
     F
    2.26
    F
    1.95
     f
    1.56
    f
    1.52
     FW
    1.51
     Fen
    1.45
    FP
    1.45
    FS
    1.44
    FF
    1.43
     FS
    1.42
    Act Density 0.658%

    No Known Activations