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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "obvious" indicating a strong emphasis on clear and apparent truths or facts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    obvious

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ligiloj
    -0.53
    cashire
    -0.53
     FileWriter
    -0.52
    ilibr
    -0.51
    veloper
    -0.51
     useDispatch
    -0.50
    TypedDataSet
    -0.49
    Rptr
    -0.49
    ynchrotron
    -0.49
     Mone
    -0.49
    POSITIVE LOGITS
     obvious
    1.73
    obvious
    1.70
    Obvious
    1.64
     obvio
    1.27
    VIOUS
    1.09
     évident
    1.06
     оче
    0.94
     evident
    0.92
     evidente
    0.88
     obviously
    0.87
    Act Density 0.011%

    No Known Activations