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

    Neuronpedia

    INDEX
    Explanations

    references to the word "saw" or its various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ches
    -0.18
    ëĿ½
    -0.17
    stk
    -0.15
    inate
    -0.15
    avar
    -0.15
    phere
    -0.15
    upro
    -0.14
    intColor
    -0.14
    odos
    -0.14
    Ñħов
    -0.14
    POSITIVE LOGITS
    dust
    0.33
    yer
    0.23
    mill
    0.23
    yers
    0.20
    ed
    0.20
    eful
    0.18
    tell
    0.18
    bones
    0.17
    onn
    0.17
    arp
    0.17
    Act Density 0.008%

    No Known Activations