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

    Neuronpedia

    INDEX
    Explanations

    terms related to specific system modes and their characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dale
    -0.24
    do
    -0.18
    wood
    -0.18
    ly
    -0.18
    role
    -0.17
    to
    -0.17
    nya
    -0.17
    nt
    -0.17
    roll
    -0.17
    roads
    -0.16
    POSITIVE LOGITS
    led
    0.25
    ONGL
    0.20
    hift
    0.18
     operand
    0.18
    ities
    0.17
    åĪ¥
    0.17
    lessly
    0.17
    less
    0.17
    illard
    0.17
    NotSupportedException
    0.17
    Act Density 0.029%

    No Known Activations