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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing influence and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    :http
    -0.14
    atar
    -0.14
    @qq
    -0.13
    ä¹ĭä¸Ģ
    -0.13
    unce
    -0.12
    ess
    -0.12
    (||
    -0.12
    lein
    -0.12
    ='./
    -0.12
    åĸĶ
    -0.12
    POSITIVE LOGITS
     X
    0.41
     XYZ
    0.36
     xyz
    0.36
     XX
    0.35
     ABC
    0.33
     XXX
    0.33
     x
    0.33
     XY
    0.32
    XYZ
    0.32
    XX
    0.32
    Act Density 0.331%

    No Known Activations