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

    Neuronpedia

    INDEX
    Explanations

    specific phrases that indicate controversy or debate

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ายà¸Ļ
    -0.16
    æ¹
    -0.15
     Tried
    -0.15
    lea
    -0.15
    jon
    -0.15
    uni
    -0.14
    deep
    -0.14
    umi
    -0.14
    aly
    -0.14
    ollapsed
    -0.14
    POSITIVE LOGITS
    untos
    0.16
    wise
    0.16
    ONENT
    0.15
    Į¨
    0.15
     foreign
    0.15
     golden
    0.14
    orz
    0.14
    $MESS
    0.14
    .struts
    0.14
    .Align
    0.13
    Act Density 0.293%

    No Known Activations