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

    Neuronpedia

    INDEX
    Explanations

    phrases related to traffic and directional instructions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uetype
    -0.17
    ureau
    -0.16
    ofs
    -0.15
    edback
    -0.15
    ourg
    -0.15
    éĿ¢ç©į
    -0.14
    поÑģ
    -0.14
     Inn
    -0.14
     sav
    -0.14
     useClass
    -0.14
    POSITIVE LOGITS
    wards
    0.26
    ward
    0.25
    /up
    0.23
    wise
    0.18
    /down
    0.18
     direction
    0.17
    -facing
    0.17
    WARD
    0.16
    ylim
    0.16
    bias
    0.15
    Act Density 0.096%

    No Known Activations