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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate causation or logical progression

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Theſe
    -0.72
    unnitel
    -0.67
    RectangleBorder
    -0.66
    mybatisplus
    -0.65
     Abonnez
    -0.64
    InjectAttribute
    -0.64
    ResumeLayout
    -0.63
     Hase
    -0.61
     evaporated
    -0.59
     yii
    -0.59
    POSITIVE LOGITS
     through
    0.78
     באמצעות
    0.78
     Through
    0.77
     través
    0.76
    Through
    0.75
     طریق
    0.70
     durch
    0.68
    通过
    0.68
    通過
    0.68
    through
    0.65
    Act Density 0.333%

    No Known Activations