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

    Neuronpedia

    INDEX
    Explanations

    metrics related to vehicle performance specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iamond
    -0.15
    unya
    -0.15
    cé
    -0.15
    het
    -0.14
    cale
    -0.14
    rava
    -0.14
    roup
    -0.14
     srd
    -0.14
     dear
    -0.14
     hunted
    -0.14
    POSITIVE LOGITS
     torque
    0.21
     Force
    0.17
     force
    0.17
     impress
    0.16
     Tor
    0.16
     Dane
    0.15
    orque
    0.15
     Continent
    0.15
     push
    0.15
     pressure
    0.15
    Act Density 0.004%

    No Known Activations