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

    Neuronpedia

    INDEX
    Explanations

    content related to descriptions and background information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    #:
    -0.15
     Nixon
    -0.14
    are
    -0.13
    pite
    -0.13
     punct
    -0.13
    ahy
    -0.13
     Nigel
    -0.13
     stalled
    -0.13
     Superintendent
    -0.13
    anj
    -0.13
    POSITIVE LOGITS
    784
    0.21
    676
    0.16
    utor
    0.16
    orrent
    0.15
    icut
    0.15
    otos
    0.15
    å®Į
    0.15
    annon
    0.15
    åºľ
    0.15
    ampp
    0.14
    Act Density 0.101%

    No Known Activations