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

    Neuronpedia

    INDEX
    Explanations

    words related to directions or motion

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    cu
    -0.84
    drivers
    -0.78
    chin
    -0.73
     held
    -0.68
    chell
    -0.67
     briefed
    -0.67
    etimes
    -0.65
    cham
    -0.65
     crawled
    -0.65
     Cosponsors
    -0.64
    POSITIVE LOGITS
     infinity
    0.89
    wards
    0.88
     adulthood
    0.85
    WARD
    0.83
     extinction
    0.76
    ente
    0.75
     fruition
    0.74
     toward
    0.73
     solving
    0.70
     submission
    0.70
    Act Density 0.035%

    No Known Activations