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

    Neuronpedia

    INDEX
    Explanations

    verbs and phrases indicating movement or departure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ibi
    -0.15
    iston
    -0.15
    758
    -0.15
    016
    -0.15
    rang
    -0.15
    ono
    -0.15
    ullet
    -0.14
    istrat
    -0.14
    bject
    -0.14
    utz
    -0.14
    POSITIVE LOGITS
     heading
    0.31
     headed
    0.30
     toward
    0.29
     towards
    0.28
     bound
    0.26
    heading
    0.24
     destination
    0.23
     Heading
    0.23
    Heading
    0.23
    åīįå¾Ģ
    0.22
    Act Density 0.079%

    No Known Activations