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

    Neuronpedia

    INDEX
    Explanations

    phrases related to perspectives from the outside looking in

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    anwhile
    -0.90
    enegger
    -0.80
    iji
    -0.79
    lda
    -0.78
    ruary
    -0.75
    lication
    -0.74
    ministic
    -0.71
    dayName
    -0.71
    fect
    -0.70
    _-
    -0.70
    POSITIVE LOGITS
     workings
    0.89
     observer
    0.81
     world
    0.79
     linebackers
    0.72
     flap
    0.72
     diameter
    0.72
     dimensions
    0.71
     linebacker
    0.71
    world
    0.70
     appearance
    0.69
    Act Density 0.086%

    No Known Activations