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

    Neuronpedia

    INDEX
    Explanations

    interviews or conversations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "spoke" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rypt
    -0.72
    reci
    -0.69
    inner
    -0.69
    anny
    -0.68
    adjusted
    -0.65
    1600
    -0.65
     Ryder
    -0.64
    allows
    -0.63
    ritional
    -0.60
    fal
    -0.60
    POSITIVE LOGITS
     Cosponsors
    0.87
     voic
    0.80
     aloud
    0.74
     mute
    0.73
     artic
    0.71
     extensively
    0.71
     transcripts
    0.71
     harshly
    0.71
     spoken
    0.71
     UID
    0.70
    Act Density 0.025%

    No Known Activations