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

    Neuronpedia

    INDEX
    Explanations

    phrases that contain the word "type" in a technical context

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of media or content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Kore
    -0.71
     shin
    -0.65
     proport
    -0.62
     corners
    -0.61
    ITNESS
    -0.61
     board
    -0.59
     stead
    -0.59
     gul
    -0.58
     pedal
    -0.57
     quad
    -0.57
    POSITIVE LOGITS
    type
    0.92
    faces
    0.88
    folios
    0.87
    typ
    0.87
    ahead
    0.85
    casting
    0.85
    etting
    0.85
    face
    0.83
    of
    0.82
    alias
    0.81
    Act Density 0.006%

    No Known Activations