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

    Neuronpedia

    INDEX
    Explanations

    phrases related to economic and political concepts

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to ideology and its critique

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     GEAR
    -0.82
     Playoffs
    -0.75
    ramid
    -0.71
     utilizing
    -0.70
     Completed
    -0.69
     Pipeline
    -0.68
     MAP
    -0.66
    Multiple
    -0.66
     Mandatory
    -0.66
    Phase
    -0.66
    POSITIVE LOGITS
     admire
    0.87
     humour
    0.86
     modesty
    0.84
     confess
    0.83
     sophistic
    0.83
     doubtless
    0.82
     flattering
    0.82
     cynicism
    0.81
     philosophers
    0.81
     prud
    0.80
    Act Density 1.553%

    No Known Activations