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

    Neuronpedia

    INDEX
    Explanations

    actions involving physical movements

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    cia
    -0.85
    eka
    -0.75
    si
    -0.75
    ossier
    -0.72
    redo
    -0.71
    vu
    -0.69
    price
    -0.68
    cens
    -0.67
    lihood
    -0.67
    see
    -0.66
    POSITIVE LOGITS
     furiously
    0.93
     frantically
    0.87
    redients
    0.87
     selfies
    0.79
     stuff
    0.74
     things
    0.74
     dishes
    0.73
     assignments
    0.73
     oneself
    0.71
     breaths
    0.70
    Act Density 0.579%

    No Known Activations