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

    Neuronpedia

    INDEX
    Explanations

    lists or articles containing tips on various subjects

    oai_token-act-pair · gpt-3.5-turbo

    phrases and words related to advice or recommendations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Bom
    -0.69
    overe
    -0.66
    etheus
    -0.65
     Canad
    -0.64
    ONT
    -0.64
     sclerosis
    -0.64
    yss
    -0.62
    ufact
    -0.62
    ãĥĺãĥ©
    -0.61
    aughter
    -0.60
    POSITIVE LOGITS
    tips
    0.93
    heet
    0.91
     guide
    0.90
    Tips
    0.88
     tips
    0.88
     Tips
    0.85
     glean
    0.85
     Helpful
    0.84
    giving
    0.84
    kit
    0.84
    Act Density 0.075%

    No Known Activations