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

    Neuronpedia

    INDEX
    Explanations

    phrases related to teamwork and collaboration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ieber
    -0.16
    ourg
    -0.14
    vore
    -0.14
    HAV
    -0.14
    δÏİ
    -0.14
    ndx
    -0.14
    gif
    -0.14
    lever
    -0.14
     ввод
    -0.13
    roduced
    -0.13
    POSITIVE LOGITS
     heading
    0.40
     headed
    0.40
     Heading
    0.30
     travel
    0.30
     goes
    0.30
     journey
    0.30
     goto
    0.29
    åīįå¾Ģ
    0.28
     went
    0.28
    heading
    0.28
    Act Density 0.323%

    No Known Activations