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

    Neuronpedia

    INDEX
    Explanations

    descriptive details about characters and settings in a narrative

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Missile
    -0.56
     geslacht
    -0.52
     Slee
    -0.51
    дие
    -0.50
    IsContent
    -0.49
     turban
    -0.49
    itzende
    -0.48
    __;
    -0.47
     propOrder
    -0.47
    Slee
    -0.47
    POSITIVE LOGITS
     walk
    3.13
     walking
    3.02
    walk
    2.81
     walks
    2.73
     walked
    2.73
     WALK
    2.70
     Walk
    2.70
    walking
    2.68
    Walk
    2.67
     Walking
    2.65
    Act Density 0.332%

    No Known Activations