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

    Neuronpedia

    INDEX
    Explanations

    numbers representing specific ranges or quantities

    oai_token-act-pair · gpt-3.5-turbo

    numerical values and specific quantities related to time or age

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Proposition
    -0.79
     Mystery
    -0.68
     Clapper
    -0.62
    uden
    -0.62
     Appl
    -0.62
     Guilty
    -0.61
     PROG
    -0.60
     Gleaming
    -0.59
     Maurit
    -0.58
     BART
    -0.57
    POSITIVE LOGITS
    -)
    1.05
    -,
    0.98
    -[
    0.92
    -
    0.92
    icular
    0.85
    âĢij
    0.83
    -"
    0.83
    âĢIJ
    0.82
    kHz
    0.79
    outheastern
    0.79
    Act Density 0.154%

    No Known Activations