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

    Neuronpedia

    INDEX
    Explanations

    instances of user inquiries and expressions of personal experiences or preferences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uld
    -0.16
    anke
    -0.16
    олод
    -0.14
    oard
    -0.14
    arin
    -0.14
    isposable
    -0.14
    è³¢
    -0.13
    дн
    -0.13
    croll
    -0.13
    dge
    -0.13
    POSITIVE LOGITS
     haven
    0.23
     am
    0.17
    eren
    0.17
     have
    0.16
     noticed
    0.15
    haven
    0.15
     Haven
    0.15
     cannot
    0.15
     found
    0.15
     although
    0.15
    Act Density 0.161%

    No Known Activations