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

    Neuronpedia

    INDEX
    Explanations

    expressions of uncertainty or inquiry

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ModelSerializer
    -0.49
    SourceChecksum
    -0.42
    DataAnnotations
    -0.41
     lienzo
    -0.39
     campamento
    -0.38
     plomo
    -0.38
    Hentet
    -0.37
    FormState
    -0.36
     avances
    -0.35
     cheiro
    -0.35
    POSITIVE LOGITS
    Thought
    0.52
     PeEnEo
    0.51
    openqa
    0.51
    RequestQueue
    0.48
     THOUGHT
    0.48
     Thought
    0.48
    Thinking
    0.48
     Thinking
    0.47
    thought
    0.47
    uz
    0.46
    Act Density 0.391%

    No Known Activations