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

    Neuronpedia

    INDEX
    Explanations

    phrases related to specific events or celebrations, such as parties or holidays

    oai_token-act-pair · gpt-3.5-turbo

    instances of commas in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ursive
    -0.73
    ocl
    -0.68
    usp
    -0.68
    igham
    -0.67
    ophon
    -0.66
     guiActiveUn
    -0.66
    escription
    -0.66
    utsche
    -0.65
    Information
    -0.65
    utive
    -0.64
    POSITIVE LOGITS
     huh
    1.33
     eh
    1.22
     haha
    1.14
     anyways
    1.02
     anyway
    0.99
     albeit
    0.92
     ya
    0.90
     lol
    0.90
     yeah
    0.89
     lest
    0.87
    Act Density 0.473%

    No Known Activations