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

    Neuronpedia

    INDEX
    Explanations

    instances of conditional phrases and logical structures in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ses
    -0.18
     (
    -0.15
    phans
    -0.15
    eer
    -0.15
    rael
    -0.14
    ãĤ§
    -0.14
    bra
    -0.14
    ients
    -0.14
    ipment
    -0.14
    @nate
    -0.14
    POSITIVE LOGITS
    adays
    0.29
    oret
    0.28
    gether
    0.25
    oretical
    0.25
    etheless
    0.22
    atre
    0.21
    bidden
    0.21
    ÑįÑĤомÑĥ
    0.19
    quarters
    0.19
    jourd
    0.19
    Act Density 0.151%

    No Known Activations