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

    Neuronpedia

    INDEX
    Explanations

    phrases or words signaling a change of topic or introducing additional information

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "by the way."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĸļ
    -0.81
    ifer
    -0.79
    incinn
    -0.76
    ufact
    -0.74
    anmar
    -0.72
    arij
    -0.69
    natureconservancy
    -0.66
    vol
    -0.65
    adden
    -0.65
     pursuit
    -0.64
    POSITIVE LOGITS
    points
    0.80
    point
    0.74
    ward
    0.69
    WARD
    0.69
     Remastered
    0.69
    KEY
    0.67
    liness
    0.66
    sey
    0.66
    !:
    0.64
    âĢ¦)
    0.63
    Act Density 0.013%

    No Known Activations