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

    Neuronpedia

    INDEX
    Explanations

    references to leaves in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    addock
    -0.18
     alarm
    -0.16
    á»ijng
    -0.16
    ToLeft
    -0.14
     linspace
    -0.14
     alarms
    -0.14
    irc
    -0.14
     Alarm
    -0.14
    amente
    -0.14
    phalt
    -0.13
    POSITIVE LOGITS
    leting
    0.31
    let
    0.30
    y
    0.28
    lets
    0.28
    ãĥ¬ãĥĥãĥĪ
    0.23
    LET
    0.22
    stalk
    0.22
    less
    0.21
    leted
    0.21
    ãģ£ãģ±
    0.21
    Act Density 0.016%

    No Known Activations