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

    Neuronpedia

    INDEX
    Explanations

    mentions of controversial political figures and topics

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks and their context in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     displacement
    -0.94
     disciplines
    -0.89
     hatch
    -0.84
     encomp
    -0.83
     colours
    -0.83
     prec
    -0.82
     foc
    -0.81
     unexpl
    -0.81
     strugg
    -0.81
     hydrogen
    -0.81
    POSITIVE LOGITS
    Anyway
    1.72
    UPDATE
    1.59
    Yesterday
    1.54
    SPONSORED
    1.51
    Apparently
    1.51
    Advertisement
    1.46
    Via
    1.44
    Here
    1.44
    CNN
    1.43
    Guest
    1.40
    Act Density 0.491%

    No Known Activations