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

    Neuronpedia

    INDEX
    Explanations

    phrases related to offering help or support

    oai_token-act-pair · gpt-3.5-turbo

    expressions of welcoming and inclusivity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    asus
    -0.51
     Awareness
    -0.45
    cano
    -0.45
     Centers
    -0.45
    gemony
    -0.43
    uesday
    -0.43
    eatured
    -0.43
    cour
    -0.41
    liament
    -0.41
    efe
    -0.41
    POSITIVE LOGITS
     to
    1.19
    .
    1.07
    !.
    1.03
     ;)
    1.01
     thereto
    1.00
     :)
    0.95
    !
    0.91
     TO
    0.91
    .'
    0.89
    .:
    0.89
    Act Density 0.474%

    No Known Activations