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

    Neuronpedia

    INDEX
    Explanations

    movements or actions towards a specific direction

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate position or movement within a space

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Conservatives
    -0.69
    advertising
    -0.66
     Values
    -0.63
    Released
    -0.57
     Nation
    -0.56
    cript
    -0.56
     Bible
    -0.55
     Tories
    -0.54
     spoiled
    -0.53
    llor
    -0.52
    POSITIVE LOGITS
    between
    1.23
     front
    1.16
    wards
    1.11
    animate
    1.00
     unison
    0.98
    direction
    0.97
    ching
    0.93
     circles
    0.92
     situ
    0.92
    versions
    0.92
    Act Density 0.218%

    No Known Activations