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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and indicators of excitement or emphasis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    End points of distinct content sections or information blocks, often preceding a transition to a new topic.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    New Auto-Interp
    Negative Logits
     also
    -0.07
    quia
    -0.07
    izr
    -0.06
     indeed
    -0.06
     thereby
    -0.06
    atak
    -0.06
     then
    -0.06
     other
    -0.06
     дÑĢÑĥгие
    -0.06
    άÏĥ
    -0.06
    POSITIVE LOGITS
    OPSIS
    0.08
    hattan
    0.07
    odore
    0.07
    _Lean
    0.06
     Boulevard
    0.06
    rientation
    0.06
    okers
    0.06
    Util
    0.06
    IGIN
    0.06
    soever
    0.06
    Act Density 0.003%

    No Known Activations