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

    Neuronpedia

    INDEX
    Explanations

    phrases and terms that indicate conflict or struggle

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    €”
    -0.69
    mdash
    -0.64
    ———
    -0.59
    〜
    -0.57
    َّ
    -0.54
    ���
    -0.54
     daß
    -0.53
    \'
    -0.50
    ----
    -0.50
    ”—
    -0.50
    POSITIVE LOGITS
     –
    2.02
     –,
    1.78
    –
    1.08
    –)
    1.03
     -,
    1.01
    .–
    0.94
    )–
    0.89
    ,–
    0.88
    ––––
    0.81
     -.
    0.76
    Act Density 0.249%

    No Known Activations