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

    Neuronpedia

    INDEX
    Explanations

    phrases suggesting a focus on specific historical events or societal issues

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    opers
    -0.77
    rift
    -0.76
    ħĭ
    -0.74
    ffield
    -0.71
    emy
    -0.70
    abad
    -0.69
    uble
    -0.69
    ivas
    -0.69
    vol
    -0.68
    achable
    -0.67
    POSITIVE LOGITS
     importantly
    0.89
     emphasis
    0.84
    nown
    0.81
     depends
    0.78
     irony
    0.74
     transpired
    0.74
     hinges
    0.73
     depended
    0.71
     ensued
    0.70
     Played
    0.68
    Act Density 0.061%

    No Known Activations