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

    Neuronpedia

    INDEX
    Explanations

    phrases related to asserting influence or power

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating parts of speech or references to actions and states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xual
    -0.95
    nces
    -0.82
    upt
    -0.81
    iques
    -0.76
    illac
    -0.71
    worldly
    -0.70
    gars
    -0.70
    say
    -0.70
    ezvous
    -0.69
    speak
    -0.69
    POSITIVE LOGITS
     stone
    0.82
     pig
    0.82
     coffin
    0.76
     sand
    0.75
     proverbial
    0.73
     donkey
    0.69
     coal
    0.69
     pear
    0.68
     sheep
    0.63
     pudding
    0.63
    Act Density 0.207%

    No Known Activations