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

    Neuronpedia

    INDEX
    Explanations

    phrases related to uncertainty or conditionals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    á»Ļi
    -0.15
     âĹĦ
    -0.15
     kø
    -0.14
    _DECLARE
    -0.14
    fos
    -0.14
    cona
    -0.14
    zim
    -0.14
    ault
    -0.14
    OTES
    -0.14
     Weber
    -0.14
    POSITIVE LOGITS
    å¢
    0.16
    Warnings
    0.15
    warnings
    0.14
    bere
    0.14
    uce
    0.14
    ount
    0.13
    üstü
    0.13
    /LICENSE
    0.13
    wide
    0.13
     widespread
    0.13
    Act Density 0.044%

    No Known Activations