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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legality and compliance with regulations

    oai_token-act-pair · gpt-3.5-turbo

    prepositions and their usage within sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    neys
    -0.66
     raped
    -0.61
     Doodle
    -0.60
    Crew
    -0.59
     overcame
    -0.59
    APD
    -0.59
    llan
    -0.57
     succeed
    -0.57
     FTA
    -0.56
    iae
    -0.55
    POSITIVE LOGITS
    escap
    1.26
    accessible
    1.05
    humane
    1.05
     fact
    1.02
    versely
    1.02
    authent
    1.00
    cluded
    0.99
    ked
    0.99
     essence
    0.98
    strument
    0.98
    Act Density 0.150%

    No Known Activations