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

    Neuronpedia

    INDEX
    Explanations

    transitions indicating a contrast or shift in focus

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "However."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Goth
    -0.66
    board
    -0.63
    cup
    -0.62
    stein
    -0.61
    uto
    -0.59
     award
    -0.59
    letter
    -0.58
    rieg
    -0.57
     parade
    -0.57
     speech
    -0.56
    POSITIVE LOGITS
    chery
    0.78
    CLASSIFIED
    0.78
    tons
    0.74
    lers
    0.74
     interestingly
    0.73
    theless
    0.72
    chers
    0.72
     importantly
    0.71
    BIL
    0.69
    THER
    0.67
    Act Density 0.035%

    No Known Activations