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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and question-related symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    assen
    -0.16
    ró
    -0.16
    repos
    -0.15
    amas
    -0.15
    eti
    -0.15
    CHA
    -0.15
    ãĤĩ
    -0.15
    angu
    -0.15
    polator
    -0.15
    =back
    -0.14
    POSITIVE LOGITS
    Browse
    0.20
    eness
    0.18
    /Edit
    0.18
    agger
    0.16
    .stack
    0.16
    .SE
    0.15
    /reference
    0.15
    èijĹ
    0.15
    Edit
    0.14
    184
    0.14
    Act Density 0.020%

    No Known Activations