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

    Neuronpedia

    INDEX
    Explanations

    meta-references or commentary on writing, humor, and storytelling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    们
    -0.15
    CF
    -0.14
    ãĥ¼ãĥĨ
    -0.14
    ides
    -0.14
    ince
    -0.14
     anymore
    -0.13
    ingles
    -0.13
    aris
    -0.13
     throughout
    -0.13
    ledge
    -0.13
    POSITIVE LOGITS
     involving
    0.26
     someone
    0.19
     somebody
    0.19
     called
    0.17
     involve
    0.17
    ummy
    0.16
    called
    0.15
     that
    0.15
    someone
    0.15
     somewhere
    0.15
    Act Density 0.248%

    No Known Activations