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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the concept of escape

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    igan
    -0.21
    orest
    -0.17
    .slim
    -0.15
    lou
    -0.15
    imizer
    -0.15
    ãĥ¼ãĥĩ
    -0.15
    gger
    -0.15
    rna
    -0.15
    jure
    -0.14
    iples
    -0.14
    POSITIVE LOGITS
    ooth
    0.17
    unci
    0.16
    ollar
    0.14
    0.14
    ubo
    0.14
    ä¸įäºĨ
    0.13
    419
    0.13
    ear
    0.13
    λοÏħ
    0.13
    plain
    0.13
    Act Density 0.007%

    No Known Activations