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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating direction or location

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dap
    -0.18
    alet
    -0.16
    allet
    -0.15
    anford
    -0.15
     createState
    -0.15
    deo
    -0.14
    .withOpacity
    -0.14
    dae
    -0.14
    Corner
    -0.14
    wheel
    -0.14
    POSITIVE LOGITS
     along
    0.20
     route
    0.19
     lines
    0.19
    è·¯
    0.18
     line
    0.18
     chain
    0.18
    tems
    0.18
     path
    0.17
    -lines
    0.17
     journey
    0.16
    Act Density 0.086%

    No Known Activations