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

    Neuronpedia

    INDEX
    Explanations

    expressions of agreement and disagreement in discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DSA
    -0.15
    sole
    -0.15
    873
    -0.14
    ounter
    -0.14
    ulace
    -0.14
    ocol
    -0.14
    å±ĭ
    -0.13
    cred
    -0.13
    lesh
    -0.13
    icer
    -0.13
    POSITIVE LOGITS
     sentiments
    0.20
     sentiment
    0.19
    aland
    0.18
    adeon
    0.17
     ************************************************************************
    0.16
    ä¿Ĺ
    0.16
     statement
    0.15
     about
    0.15
    adic
    0.14
    Breadcrumb
    0.14
    Act Density 0.050%

    No Known Activations