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

    Neuronpedia

    INDEX
    Explanations

    conversational elements and greetings in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     -*-č↵
    -0.14
     Homer
    -0.14
    âĶĺ
    -0.14
    izik
    -0.13
    esser
    -0.13
    romise
    -0.13
    oreal
    -0.13
    aise
    -0.13
    ently
    -0.13
    forgettable
    -0.13
    POSITIVE LOGITS
     hello
    0.73
     Hello
    0.70
    Hello
    0.62
    hello
    0.59
     Hi
    0.54
     hi
    0.53
    _hello
    0.50
    Hi
    0.49
     greeting
    0.48
     greetings
    0.46
    Act Density 0.283%

    No Known Activations