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

    Neuronpedia

    INDEX
    Explanations

    verbs related to attempting or making an effort

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the conjunction “and” to connect multiple ideas or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    houses
    -0.73
     Cros
    -0.71
     Debor
    -0.69
     Lands
    -0.63
     Powered
    -0.61
    ANC
    -0.60
    æĥ
    -0.58
    ELD
    -0.58
    sectional
    -0.58
    Mine
    -0.58
    POSITIVE LOGITS
     emulate
    1.00
     replicate
    0.91
     recreate
    0.91
     impart
    0.86
     reconcile
    0.85
     revive
    0.85
     preserve
    0.85
     predict
    0.84
     resolve
    0.84
     propagate
    0.82
    Act Density 0.019%

    No Known Activations