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

    Neuronpedia

    INDEX
    Explanations

    positive qualities or attributes, particularly related to personal character or appeal

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to charm and charisma

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ©¶æ
    -0.72
    arers
    -0.71
    alez
    -0.70
    ferred
    -0.68
    orters
    -0.66
    uden
    -0.65
    ffic
    -0.65
     GPUs
    -0.65
    ablo
    -0.65
     Printed
    -0.63
    POSITIVE LOGITS
     charm
    1.26
     charms
    1.07
    ingly
    0.92
    isma
    0.88
     Charm
    0.81
    istically
    0.78
     charisma
    0.78
     charming
    0.78
     lure
    0.77
    phal
    0.76
    Act Density 0.009%

    No Known Activations