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

    Neuronpedia

    INDEX
    Explanations

    phrases related to boldness or strong statements

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "bold" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OTOS
    -0.94
     Cheong
    -0.94
    apolis
    -0.71
    rogens
    -0.69
    rera
    -0.69
    ADS
    -0.68
    enfranch
    -0.66
    uters
    -0.66
    yip
    -0.66
     externalToEVAOnly
    -0.65
    POSITIVE LOGITS
    faced
    1.18
    ness
    1.08
    er
    1.06
    face
    0.99
    bold
    0.92
     bold
    0.90
    word
    0.83
    mouth
    0.82
    est
    0.80
    nesses
    0.80
    Act Density 0.025%

    No Known Activations