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

    Neuronpedia

    INDEX
    Explanations

    various types of ranges across different contexts and topics

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    agate
    -0.67
     Walls
    -0.59
     Matter
    -0.58
     Tycoon
    -0.57
     Doodle
    -0.53
     fusion
    -0.53
    ylan
    -0.52
     relativity
    -0.51
    anium
    -0.51
     Stories
    -0.51
    POSITIVE LOGITS
     of
    1.01
    of
    0.76
    Of
    0.75
     Of
    0.74
     OF
    0.73
     thereof
    0.73
    OF
    0.72
    Downloadha
    0.72
    atical
    0.67
    finder
    0.66
    Act Density 0.903%

    No Known Activations