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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing justification or reasons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ikan
    -0.17
    ronics
    -0.15
    locker
    -0.15
    imore
    -0.14
    avra
    -0.14
    avis
    -0.14
     juris
    -0.14
     just
    -0.13
    jes
    -0.13
    jit
    -0.13
    POSITIVE LOGITS
    soever
    0.15
    .communication
    0.14
    qli
    0.14
    _residual
    0.14
    .createCell
    0.13
     Petty
    0.13
    keh
    0.13
    imetype
    0.13
    orough
    0.13
    .xtext
    0.13
    Act Density 0.028%

    No Known Activations