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

    Neuronpedia

    INDEX
    Explanations

    phrases related to commentary or responses in written discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pron
    -0.15
    wyn
    -0.15
    utes
    -0.14
    ramer
    -0.14
    ernen
    -0.13
    iani
    -0.13
    WithURL
    -0.13
    λή
    -0.13
    tridges
    -0.13
    itou
    -0.12
    POSITIVE LOGITS
     Anonymous
    0.38
     anonymous
    0.37
    anonymous
    0.32
    Anonymous
    0.30
     anonymously
    0.28
     anon
    0.26
     someone
    0.26
     anonym
    0.24
    someone
    0.23
    onymous
    0.21
    Act Density 0.142%

    No Known Activations