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

    Neuronpedia

    INDEX
    Explanations

    political figures and their positions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Counter
    -0.71
     Chop
    -0.69
     Bend
    -0.69
     CT
    -0.67
     Jem
    -0.67
     SCP
    -0.67
     PB
    -0.66
     Ember
    -0.66
     Impact
    -0.65
     outweigh
    -0.65
    POSITIVE LOGITS
    28
    1.49
    26
    1.49
    23
    1.46
    48
    1.46
    29
    1.45
    24
    1.44
    19
    1.44
    39
    1.43
    54
    1.43
    27
    1.43
    Act Density 0.571%

    No Known Activations