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

    Neuronpedia

    INDEX
    Explanations

    words related to assertiveness and confidence

    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
     Cheong
    -0.93
    OTOS
    -0.92
    yip
    -0.69
    enfranch
    -0.67
    rogens
    -0.64
    apolis
    -0.64
    uters
    -0.62
     Relations
    -0.62
    nesota
    -0.62
    AW
    -0.62
    POSITIVE LOGITS
    faced
    1.10
    er
    1.06
    ness
    0.99
    bold
    0.95
    face
    0.93
     bold
    0.90
    itude
    0.84
     Ital
    0.84
    est
    0.81
    word
    0.81
    Act Density 0.016%

    No Known Activations