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

    Neuronpedia

    INDEX
    Explanations

    phrases related to physical body movements and gestures

    oai_token-act-pair · gpt-3.5-turbo

    physical interactions between characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     reim
    -0.78
    construct
    -0.72
    в
    -0.70
    ãĥ¯ãĥ³
    -0.65
    Thumbnail
    -0.64
     vetting
    -0.64
    UFF
    -0.64
     restruct
    -0.63
    GV
    -0.63
     reinvent
    -0.62
    POSITIVE LOGITS
     him
    0.97
     bushes
    0.84
     passers
    0.77
     imaginary
    0.77
     nearest
    0.75
     them
    0.74
     his
    0.73
     SCP
    0.70
     midfield
    0.68
     me
    0.67
    Act Density 0.259%

    No Known Activations