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

    Neuronpedia

    INDEX
    Explanations

    words related to positive or supportive actions or statements

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to encouragement or positivity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tan
    -0.70
    kos
    -0.69
    imeter
    -0.66
    die
    -0.65
    ness
    -0.65
    Base
    -0.64
    tion
    -0.64
    sth
    -0.63
    tera
    -0.62
    yx
    -0.62
    POSITIVE LOGITS
     encouraging
    3.33
     discouraging
    2.41
     reassuring
    1.78
     encouragement
    1.72
     promising
    1.68
     inviting
    1.63
     inspiring
    1.60
     enticing
    1.56
     encourage
    1.54
     fostering
    1.52
    Act Density 0.020%

    No Known Activations