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

    Neuronpedia

    INDEX
    Explanations

    pronouns and their usage in dialogue or indirect speech

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    quate
    -0.15
    usto
    -0.15
    .datas
    -0.15
    evin
    -0.15
    ulfill
    -0.14
    quip
    -0.14
    uve
    -0.14
    _MAXIMUM
    -0.14
    ihn
    -0.14
    lements
    -0.13
    POSITIVE LOGITS
     how
    0.32
     about
    0.29
     what
    0.28
     why
    0.28
     it
    0.27
     everything
    0.27
     something
    0.25
     they
    0.25
     stories
    0.25
     exactly
    0.24
    Act Density 0.088%

    No Known Activations