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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to control and modulation in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IntoConstraints
    -0.54
     actionPerformed
    -0.43
    lloworld
    -0.42
     كومونز
    -0.42
     Its
    -0.40
    fromnode
    -0.40
     its
    -0.40
     firebaseConfig
    -0.39
    AndroidJUnit
    -0.39
    fgets
    -0.39
    POSITIVE LOGITS
     themselves
    0.83
    themselves
    0.82
     själva
    0.73
     yourselves
    0.61
    their
    0.60
     theyre
    0.58
     selves
    0.57
    Their
    0.56
    they
    0.55
    彼らは
    0.52
    Act Density 1.293%

    No Known Activations