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

    Neuronpedia

    INDEX
    Explanations

    actions related to movement and interaction among characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     overnight
    -0.16
     Representation
    -0.14
    odyn
    -0.14
    alette
    -0.14
    ÐIJÑĢÑħÑĸв
    -0.14
    overn
    -0.14
     Overnight
    -0.13
    ancia
    -0.13
     Nights
    -0.13
    unker
    -0.13
    POSITIVE LOGITS
     seconds
    0.24
     gest
    0.21
    seconds
    0.21
    Seconds
    0.19
     behind
    0.18
     motion
    0.17
     grabbed
    0.17
     interrupt
    0.17
     looked
    0.16
     grab
    0.16
    Act Density 1.908%

    No Known Activations