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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the completion of a task or reaching a goal

    oai_token-act-pair · gpt-3.5-turbo

    repeated phrases or expressions indicating a condition of possession or obligation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    template
    -0.75
     è£ıç
    -0.66
    è¦ļéĨĴ
    -0.65
     tackled
    -0.64
    Spot
    -0.64
    illac
    -0.64
     guiActiveUn
    -0.63
     à¨
    -0.63
    ãĥ¯ãĥ³
    -0.60
    lished
    -0.60
    POSITIVE LOGITS
    uminati
    1.16
    inois
    0.98
    oyd
    0.96
    aday
    0.86
    umi
    0.85
    owship
    0.84
    ounge
    0.84
    ingly
    0.84
    ardless
    0.83
    ows
    0.81
    Act Density 0.023%

    No Known Activations