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

    Neuronpedia

    INDEX
    Explanations

    phrases related to government policies and regulations

    oai_token-act-pair · gpt-3.5-turbo

    repeated conjunctions in complex phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    :(
    -0.73
    Ĥİ
    -0.72
    :[
    -0.68
    odcast
    -0.67
    apter
    -0.66
    Shut
    -0.64
    IRE
    -0.64
    itans
    -0.64
    uta
    -0.62
     WARN
    -0.62
    POSITIVE LOGITS
     consequently
    1.12
     hence
    1.09
     therefore
    1.07
     thus
    1.02
     thereby
    0.96
     then
    0.94
     possibly
    0.93
    rogen
    0.90
    rogens
    0.87
     vice
    0.86
    Act Density 1.038%

    No Known Activations