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

    Neuronpedia

    INDEX
    Explanations

    references to fictional characters and their conflicts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    TagMode
    -0.50
    mphs
    -0.45
    +#+#
    -0.44
    ForKey
    -0.44
    hews
    -0.43
    θος
    -0.43
     atunci
    -0.42
    lète
    -0.42
    りする
    -0.42
     linkovi
    -0.42
    POSITIVE LOGITS
     OMITBAD
    0.85
     evil
    0.74
     SqlCommand
    0.70
    Evil
    0.65
    evil
    0.65
     scum
    0.64
     gangs
    0.60
     threats
    0.60
     Evil
    0.60
    WebServlet
    0.59
    Act Density 0.779%

    No Known Activations