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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and conjunctions, indicating sentence structure and connections between ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     –↵↵
    -0.16
     “
    -0.15
    .scalablytyped
    -0.15
    ÅĻÃŃzenÃŃ
    -0.15
     ENC
    -0.14
    arend
    -0.14
    furt
    -0.14
    Ìĥ
    -0.14
     Malk
    -0.13
    ouri
    -0.13
    POSITIVE LOGITS
    .onView
    0.17
    ;↵
    0.16
    :↵
    0.16
     |↵
    0.16
    }{↵
    0.15
    eh
    0.15
    ,↵
    0.15
    metros
    0.14
    ottie
    0.13
     Fate
    0.13
    Act Density 0.189%

    No Known Activations