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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal or political contexts

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating petitions, actions related to construction, and historical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     unfocusedRange
    -0.71
    etheless
    -0.68
     forgetting
    -0.67
     narrowing
    -0.65
    endif
    -0.65
    forcing
    -0.64
    ESCO
    -0.63
    sever
    -0.63
     Hacker
    -0.61
    too
    -0.60
    POSITIVE LOGITS
     originated
    1.30
     origin
    1.09
     resides
    1.09
     occurred
    1.05
     originate
    1.02
     resided
    0.99
     occurs
    0.97
     reside
    0.96
     occur
    0.89
     eman
    0.86
    Act Density 0.182%

    No Known Activations