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

    Neuronpedia

    INDEX
    Explanations

    calls to action prompting the reader to sign up or take action

    oai_token-act-pair · gpt-3.5-turbo

    repeated conjunctions, particularly the word "and."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ULTS
    -0.65
    arious
    -0.64
    etheus
    -0.63
    going
    -0.59
    sth
    -0.57
    eki
    -0.57
    existent
    -0.57
    paralle
    -0.56
    ays
    -0.56
    pell
    -0.55
    POSITIVE LOGITS
     enjoy
    0.76
     Save
    0.75
     receive
    0.75
    rew
    0.68
    romeda
    0.68
     donate
    0.68
     weep
    0.67
    PIN
    0.67
     join
    0.66
     save
    0.65
    Act Density 0.035%

    No Known Activations