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

    Neuronpedia

    INDEX
    Explanations

    adjectives describing the physical characteristics of objects or environments

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "thick" and its variants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DB
    -0.73
    FAULT
    -0.69
    @#&
    -0.69
    CB
    -0.67
     Million
    -0.67
     starring
    -0.67
    instead
    -0.66
    Particip
    -0.66
    ARCH
    -0.65
    pheus
    -0.64
    POSITIVE LOGITS
    ened
    1.27
    ening
    1.26
    nesses
    1.23
    ener
    1.05
    ness
    0.99
    layer
    0.94
    ly
    0.92
    entimes
    0.92
    ned
    0.91
    ciating
    0.90
    Act Density 0.015%

    No Known Activations