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

    Neuronpedia

    INDEX
    Explanations

    terms related to speed and acceleration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    udit
    -0.17
    ason
    -0.17
    cul
    -0.16
    laz
    -0.16
    cury
    -0.15
    aut
    -0.14
    kind
    -0.14
    attend
    -0.14
    arend
    -0.14
    £½
    -0.14
    POSITIVE LOGITS
    ily
    0.33
    sters
    0.28
    ster
    0.26
    ier
    0.25
    ometer
    0.23
    iness
    0.23
    iest
    0.20
    0.20
    boat
    0.20
    .Speed
    0.19
    Act Density 0.021%

    No Known Activations