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

    Neuronpedia

    INDEX
    Explanations

    actions or scenarios involving falling from a height

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    urg
    -0.72
    ihu
    -0.67
    ounters
    -0.67
    Dial
    -0.65
    outhern
    -0.64
    don
    -0.63
    HOU
    -0.63
    ilingual
    -0.62
    PN
    -0.62
    çĶ°
    -0.62
    POSITIVE LOGITS
     ceiling
    1.01
     grace
    1.00
     ceilings
    0.90
     cliffs
    0.90
     cliff
    0.88
     trees
    0.85
     roof
    0.84
     window
    0.83
     balcony
    0.83
     bushes
    0.81
    Act Density 0.121%

    No Known Activations