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

    Neuronpedia

    INDEX
    Explanations

    objects or materials with specific characteristics, such as stainless steel or glass

    oai_token-act-pair · gpt-3.5-turbo

    words related to specific concepts or classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    assies
    -0.67
    ernels
    -0.61
    rooms
    -0.59
     Machines
    -0.59
    events
    -0.57
     Rooms
    -0.57
    lees
    -0.56
    tics
    -0.56
    eworks
    -0.56
    sites
    -0.56
    POSITIVE LOGITS
     spokesperson
    0.56
     standpoint
    0.56
     statement
    0.54
     apology
    0.53
     illustration
    0.53
     sized
    0.52
     piece
    0.52
    atical
    0.51
    ozy
    0.51
    ixtape
    0.51
    Act Density 0.664%

    No Known Activations