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

    Neuronpedia

    INDEX
    Explanations

    referential or self-descriptive phrases and statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     kader
    -0.55
    határoz
    -0.54
     sonhos
    -0.53
    jíma
    -0.49
     unut
    -0.48
    its
    -0.48
     Gefäng
    -0.48
    hdessä
    -0.48
     tradição
    -0.48
    uts
    -0.47
    POSITIVE LOGITS
    IntoConstraints
    0.87
    ViewInit
    0.86
    kegaard
    0.80
    )";
    0.79
     HttpNotFound
    0.76
     aware
    0.74
     youre
    0.74
     myſelf
    0.73
     yourself
    0.73
    stateProvider
    0.72
    Act Density 0.738%

    No Known Activations