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

    Neuronpedia

    INDEX
    Explanations

    words related to speaking or communication

    oai_token-act-pair · gpt-3.5-turbo

    instances of speaking or singing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Solitaire
    -0.73
     sunset
    -0.64
     difficulty
    -0.60
     Sunset
    -0.60
     freezing
    -0.58
     eas
    -0.57
     beta
    -0.55
     Twilight
    -0.54
     blocking
    -0.54
    oug
    -0.53
    POSITIVE LOGITS
     speaks
    3.39
     speak
    1.98
     spoke
    1.83
     communicates
    1.80
     listens
    1.54
     reflects
    1.51
     discusses
    1.51
     expresses
    1.50
     translates
    1.49
     sings
    1.44
    Act Density 0.017%

    No Known Activations