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

    Neuronpedia

    INDEX
    Explanations

    prepositional phrases indicating position or location beneath something

    oai_token-act-pair · gpt-3.5-turbo

    words related to locations or objects positioned beneath something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    QL
    -0.87
    olkien
    -0.80
    ACY
    -0.77
    videos
    -0.76
    76561
    -0.73
    yssey
    -0.71
    FF
    -0.69
    OB
    -0.69
    uden
    -0.68
    UFF
    -0.68
    POSITIVE LOGITS
     shoulders
    1.06
     horizon
    1.02
     cliffs
    0.97
     shoulder
    0.94
     layers
    0.94
     veil
    0.92
     railing
    0.89
     canopy
    0.87
     ribs
    0.85
     bushes
    0.85
    Act Density 0.194%

    No Known Activations