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

    Neuronpedia

    INDEX
    Explanations

    positive adjectives indicating high praise or admiration

    oai_token-act-pair · gpt-3.5-turbo

    expressions of positive sentiment and enthusiasm

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    racuse
    -0.66
    ©¶æ
    -0.65
     fewer
    -0.61
    ublic
    -0.60
    omsky
    -0.60
    mbudsman
    -0.59
    çīĪ
    -0.58
    oided
    -0.58
    avez
    -0.58
     plurality
    -0.57
    POSITIVE LOGITS
    !!!!
    1.24
    !!!
    1.23
    !!
    1.23
    !
    1.20
    !!!!!
    1.19
    !:
    1.16
    !.
    1.14
    !!!!!!!!
    1.09
    !"
    1.03
    ly
    1.01
    Act Density 0.141%

    No Known Activations