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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "both."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Autoritní
    -0.75
    abetes
    -0.67
    ViewFeatures
    -0.67
    parsedMessage
    -0.65
     pinulongan
    -0.63
    pozdrawiam
    -0.63
     beginnetje
    -0.60
    bonsoir
    -0.58
    ︎
    -0.58
    bonjour
    -0.58
    POSITIVE LOGITS
     Each
    1.17
     Many
    1.16
    They
    1.15
    Many
    1.14
    These
    1.14
     Such
    1.14
    Each
    1.13
    Such
    1.12
    This
    1.11
     These
    1.10
    Act Density 0.162%

    No Known Activations