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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating instructions or requirements

    oai_token-act-pair · gpt-3.5-turbo

    future actions and expectations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ocular
    -0.75
    jam
    -0.67
    DAQ
    -0.64
    Tok
    -0.62
    minecraft
    -0.61
     traged
    -0.59
    gerald
    -0.59
    Kal
    -0.59
    Angelo
    -0.59
     lobb
    -0.58
    POSITIVE LOGITS
     probably
    0.93
     undoubtedly
    0.93
     doubtless
    0.92
     need
    0.90
     notice
    0.88
     unavoid
    0.86
     discover
    0.83
     surely
    0.83
     find
    0.83
     have
    0.80
    Act Density 0.090%

    No Known Activations