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

    Neuronpedia

    INDEX
    Explanations

    references to "samples" or instances of example content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    BLIC
    -0.92
    redit
    -0.88
    die
    -0.87
    ankind
    -0.87
    iencies
    -0.83
    rone
    -0.79
    encers
    -0.79
    friends
    -0.78
    ledge
    -0.76
    lean
    -0.76
    POSITIVE LOGITS
     wording
    0.92
     usage
    0.91
     subp
    0.88
     sized
    0.82
     listing
    0.77
     illustration
    0.76
     text
    0.75
     chapter
    0.74
     sketch
    0.73
     sample
    0.72
    Act Density 0.021%

    No Known Activations