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

    Neuronpedia

    INDEX
    Explanations

    interrogative phrases starting with "Which."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sson
    -0.15
    loff
    -0.15
    uto
    -0.15
    ran
    -0.15
    ict
    -0.14
    loid
    -0.14
     behalf
    -0.14
    udiantes
    -0.14
    ald
    -0.14
    ault
    -0.14
    POSITIVE LOGITS
    soever
    0.36
    -ever
    0.27
     direction
    0.25
     ones
    0.23
    /how
    0.23
     именно
    0.22
     Wich
    0.21
     way
    0.21
    -way
    0.20
     among
    0.20
    Act Density 0.034%

    No Known Activations