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

    Neuronpedia

    INDEX
    Explanations

    prompts or calls to action for further engagement or information

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "more"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xtap
    -0.92
    liest
    -0.79
    ĺħ
    -0.78
    Runner
    -0.70
    ader
    -0.69
    Fram
    -0.66
    Enlarge
    -0.66
    ãĥ¼ãĥĨãĤ£
    -0.66
    oes
    -0.65
    nikov
    -0.65
    POSITIVE LOGITS
     than
    1.18
     stringent
    1.02
     sophisticated
    0.98
     manageable
    0.96
     elaborate
    0.95
     efficient
    0.94
     advanced
    0.93
     detailed
    0.92
     complicated
    0.91
     expensive
    0.89
    Act Density 0.142%

    No Known Activations