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

    Neuronpedia

    INDEX
    Explanations

    phrases related to evaluation or critique

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "that" used in various contexts related to opinions, critiques, or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ussia
    -0.85
    owder
    -0.85
    oby
    -0.72
    asures
    -0.70
    este
    -0.70
    thro
    -0.69
    ¶ħ
    -0.69
    rypt
    -0.68
    izont
    -0.67
    cycles
    -0.67
    POSITIVE LOGITS
    cher
    0.97
     begs
    0.91
     includes
    0.91
     sounds
    0.86
     leaves
    0.85
     doesn
    0.83
     culminated
    0.83
     pesky
    0.82
     hasn
    0.81
     translates
    0.81
    Act Density 0.111%

    No Known Activations