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

    Neuronpedia

    INDEX
    Explanations

    punctuation and delimiters in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inspace
    -0.19
    ectl
    -0.15
    izarre
    -0.14
    dff
    -0.14
    ŀæĢ§
    -0.14
    udeau
    -0.14
    Ðħ
    -0.14
    acks
    -0.14
    ledged
    -0.14
     sibling
    -0.14
    POSITIVE LOGITS
    0.24
    0.23
    0.22
    0.20
    0.20
    0.20
    0.20
    0.19
    0.18
    0.18
    Act Density 0.008%

    No Known Activations