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

    Neuronpedia

    INDEX
    Explanations

    names or descriptions indicating significant importance or impact in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating significant contributions or roles in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Self
    -0.76
     fung
    -0.75
     limitation
    -0.74
    Cause
    -0.70
    Appearance
    -0.68
    venge
    -0.67
     immortality
    -0.65
    heit
    -0.64
    Fine
    -0.64
    ember
    -0.64
    POSITIVE LOGITS
     drafting
    0.92
     unsuccessful
    0.91
     unsuccessfully
    0.87
     pioneering
    0.86
     founding
    0.81
    utive
    0.81
    rador
    0.79
    umenthal
    0.79
     extensively
    0.75
     lia
    0.73
    Act Density 0.392%

    No Known Activations