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

    Neuronpedia

    INDEX
    Explanations

    references to dates and numbers

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    agara
    -0.72
    ches
    -0.70
    ufact
    -0.68
    hunt
    -0.68
    alyses
    -0.67
    ihad
    -0.67
    tern
    -0.67
    warts
    -0.66
    nam
    -0.64
    onymous
    -0.63
    POSITIVE LOGITS
    px
    0.83
    lbs
    0.80
    ocity
    0.79
     ILCS
    0.78
    s
    0.78
    Hz
    0.73
     MHz
    0.70
    5
    0.70
    rpm
    0.70
     metres
    0.70
    Act Density 0.060%

    No Known Activations