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

    Neuronpedia

    INDEX
    Explanations

    phrases related to driving or vehicles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isd
    -0.18
    ilde
    -0.17
    ounds
    -0.16
    xin
    -0.15
    mach
    -0.15
    ares
    -0.15
    ary
    -0.14
    ipc
    -0.14
    iser
    -0.14
    sg
    -0.14
    POSITIVE LOGITS
    haft
    0.29
    .drive
    0.20
    urge
    0.19
    away
    0.19
     shaft
    0.17
    _license
    0.16
    /dr
    0.16
    -driving
    0.16
    ered
    0.15
    -drive
    0.15
    Act Density 0.032%

    No Known Activations