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

    Neuronpedia

    INDEX
    Explanations

    phrases related to professional roles and achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     defense
    -0.40
    Referencias
    -0.39
    escape
    -0.38
     way
    -0.38
    au
    -0.37
     escape
    -0.35
    ifun
    -0.35
    interpolation
    -0.35
    ganggu
    -0.35
    ellino
    -0.35
    POSITIVE LOGITS
    таратура
    0.54
     تضيفلها
    0.50
    findpost
    0.49
     surla
    0.44
    IBarButtonItem
    0.43
     girdle
    0.41
     tevens
    0.41
     possessed
    0.40
     represented
    0.40
    GEBURTSDATUM
    0.40
    Act Density 0.285%

    No Known Activations