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

    Neuronpedia

    INDEX
    Explanations

    language related to setting goals and objectives

    oai_token-act-pair · gpt-3.5-turbo

    statements related to goals and intentions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eor
    -0.72
     emits
    -0.66
    eus
    -0.64
     Ago
    -0.64
    haw
    -0.63
     Happ
    -0.62
    ython
    -0.61
    quin
    -0.61
     Neighbor
    -0.60
     Fault
    -0.59
    POSITIVE LOGITS
     unclear
    0.76
     moot
    0.75
     maximizing
    0.75
     simplicity
    0.75
     simple
    0.72
     laud
    0.70
     clear
    0.69
     therefore
    0.69
     always
    0.69
     undoubtedly
    0.68
    Act Density 0.179%

    No Known Activations