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

    Neuronpedia

    INDEX
    Explanations

    phrases that express uncertainty or subjective opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OGND
    -1.21
    цездатний
    -1.02
    ImageContext
    -0.99
    ItemBackground
    -0.96
    Vidite
    -0.94
     wireType
    -0.93
     Wikimedijinoj
    -0.93
     intptr
    -0.93
    LookAnd
    -0.90
     الحره
    -0.90
    POSITIVE LOGITS
    .
    0.54
     until
    0.46
     p
    0.45
     or
    0.42
    v
    0.42
     fer
    0.42
    until
    0.41
     Until
    0.41
    )
    0.40
     ε
    0.39
    Act Density 0.180%

    No Known Activations