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

    Neuronpedia

    INDEX
    Explanations

    phrases containing an action followed by a statement of who said or will do the action

    oai_token-act-pair · gpt-3.5-turbo

    statements attributed to sources or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cffffcc
    -0.75
    ãĥ´
    -0.71
    otin
    -0.71
    è¯
    -0.68
    zin
    -0.67
    ãĥ¡
    -0.66
    hyde
    -0.66
    matter
    -0.65
    ldom
    -0.64
    Translation
    -0.64
    POSITIVE LOGITS
     yesterday
    0.88
     its
    0.81
     goodbye
    0.79
     Thursday
    0.76
     Monday
    0.75
     Wednesday
    0.75
    eworks
    0.73
     earlier
    0.72
     Tuesday
    0.71
     Friday
    0.70
    Act Density 0.170%

    No Known Activations