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

    Neuronpedia

    INDEX
    Explanations

    discussions surrounding social issues and personal experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     :-)
    -0.17
     sez
    -0.16
    OK
    -0.16
    amping
    -0.16
    Anyway
    -0.15
    culo
    -0.14
    dit
    -0.14
     надо
    -0.13
    ego
    -0.13
    uggle
    -0.13
    POSITIVE LOGITS
     amongst
    0.23
     surrounding
    0.22
     whilst
    0.21
     due
    0.21
     ãĥ¼
    0.21
     seperate
    0.20
    -esque
    0.19
     strictly
    0.19
     towards
    0.19
     within
    0.19
    Act Density 1.332%

    No Known Activations