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

    Neuronpedia

    INDEX
    Explanations

    phrases or sentences starting with "That"

    oai_token-act-pair · gpt-3.5-turbo

    phrases that begin with "That" to indicate statements or observations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ¶ħ
    -0.81
    emis
    -0.78
    oby
    -0.77
    ussia
    -0.77
    ccoli
    -0.75
    owder
    -0.74
    asures
    -0.73
    este
    -0.71
    rypt
    -0.71
    20439
    -0.71
    POSITIVE LOGITS
     includes
    1.02
     begs
    0.98
     doesn
    0.97
    cher
    0.96
     means
    0.94
     leaves
    0.93
     sounds
    0.93
     said
    0.92
     brings
    0.92
     hasn
    0.91
    Act Density 0.099%

    No Known Activations