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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and casual conversational elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ipur
    -0.17
    åºĶå½ĵ
    -0.15
    SocketAddress
    -0.14
    lector
    -0.14
    idders
    -0.14
    raÄį
    -0.14
    zman
    -0.13
    ernet
    -0.13
    amus
    -0.13
    kbd
    -0.13
    POSITIVE LOGITS
     Check
    0.30
     Want
    0.29
    Want
    0.28
    Check
    0.28
     want
    0.28
     Join
    0.26
     Come
    0.26
     come
    0.25
     Need
    0.25
    Join
    0.25
    Act Density 0.425%

    No Known Activations