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

    Neuronpedia

    INDEX
    Explanations

    compound words and hyphenated terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    egative
    -0.28
     latter
    -0.27
    olume
    -0.24
    quiv
    -0.23
    eneric
    -0.22
    ritten
    -0.21
    coration
    -0.21
    flammatory
    -0.21
    formance
    -0.21
    orthy
    -0.20
    POSITIVE LOGITS
    /-
    0.20
    i
    0.17
    cluding
    0.17
    .blogspot
    0.16
    ropriate
    0.15
    TRS
    0.15
    ousand
    0.15
    iard
    0.15
    ftware
    0.15
    s
    0.15
    Act Density 0.175%

    No Known Activations