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

    Neuronpedia

    INDEX
    Explanations

    statements related to policies, regulations, actions, or states of being

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to regulatory or governmental discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .–
    -0.62
    .</
    -0.62
     ..."
    -0.61
    bury
    -0.60
    -"
    -0.59
    fil
    -0.57
    .","
    -0.57
    croft
    -0.56
    ../
    -0.55
    Mine
    -0.55
    POSITIVE LOGITS
     meanwhile
    1.03
     also
    1.01
     furthermore
    0.99
     moreover
    0.98
     therefore
    0.93
     however
    0.88
     certainly
    0.88
     undoubtedly
    0.84
     thus
    0.78
     doubtless
    0.76
    Act Density 0.760%

    No Known Activations