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

    Neuronpedia

    INDEX
    Explanations

    phrases related to uncertainty and conditions that may or may not occur

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     emphat
    -0.96
     desir
    -0.94
     inconce
    -0.93
     disagre
    -0.91
     effe
    -0.89
     increa
    -0.87
     fuf
    -0.87
     unwarran
    -0.86
     suspic
    -0.86
     perfet
    -0.85
    POSITIVE LOGITS
     will
    0.71
    will
    0.70
    Will
    0.61
     sẽ
    0.58
     Will
    0.57
     gawas
    0.57
    Dichloroethane
    0.52
     WILL
    0.51
    Dichlorobenzene
    0.50
    queline
    0.50
    Act Density 0.290%

    No Known Activations