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

    Neuronpedia

    INDEX
    Explanations

    names of sports players or teams

    oai_token-act-pair · gpt-3.5-turbo

    parentheses in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     wre
    -0.75
     dow
    -0.73
     entitle
    -0.69
     hazards
    -0.68
     retard
    -0.67
     rog
    -0.67
     fres
    -0.67
    emonic
    -0.65
    aily
    -0.65
     ris
    -0.64
    POSITIVE LOGITS
    formerly
    1.48
    which
    1.38
    including
    1.29
    although
    1.29
    pictured
    1.26
    excluding
    1.26
    mostly
    1.24
    whose
    1.24
    both
    1.23
    albeit
    1.22
    Act Density 0.169%

    No Known Activations