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

    Neuronpedia

    INDEX
    Explanations

    words related to physical actions or movements

    oai_token-act-pair · gpt-3.5-turbo

    references to running, jumping, and fast-paced movement in gaming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     confidentiality
    -0.74
    amily
    -0.71
     jurisd
    -0.69
     sequest
    -0.69
     Identity
    -0.68
    dated
    -0.66
     buyer
    -0.64
     personalized
    -0.64
     confidential
    -0.64
     indemn
    -0.63
    POSITIVE LOGITS
     upright
    0.98
     dodging
    0.96
     crou
    0.95
     distances
    0.94
     motions
    0.93
     dodge
    0.92
     backwards
    0.92
     movements
    0.91
     sideways
    0.90
     motion
    0.90
    Act Density 0.335%

    No Known Activations