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

    Neuronpedia

    INDEX
    Explanations

    the term "Ant," potentially reflecting references to ants or related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ThroughAttribute
    -0.86
    ValueStyle
    -0.85
    SBATCH
    -0.76
    GraphicsUnit
    -0.74
    TestingModule
    -0.70
    quelize
    -0.67
     zvuky
    -0.67
    ScopeManager
    -0.66
     createSlice
    -0.65
     useRouter
    -0.64
    POSITIVE LOGITS
     Ant
    1.11
     ant
    1.03
    Ant
    1.01
    ant
    0.78
    lambda
    0.74
     lambda
    0.60
     reality
    0.56
    ıyordu
    0.55
    mauri
    0.54
    smart
    0.51
    Act Density 0.093%

    No Known Activations