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

    Neuronpedia

    INDEX
    Explanations

    questions that start with the word "What."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     bothers
    -0.18
     quot
    -0.15
     bother
    -0.15
    kop
    -0.14
    979
    -0.14
    ault
    -0.14
    ubi
    -0.14
    ãĥ¼ãĥ¬
    -0.14
    viron
    -0.14
    {{
    -0.13
    POSITIVE LOGITS
     do
    0.25
     kind
    0.18
    :Register
    0.17
    soever
    0.16
    ToProps
    0.16
     does
    0.15
    setter
    0.15
    باد
    0.15
    .LookAndFeel
    0.15
     exactly
    0.15
    Act Density 0.066%

    No Known Activations