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

    Neuronpedia

    INDEX
    Explanations

    acknowledgments and references to awareness or understanding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    picker
    -0.17
    eko
    -0.15
    %M
    -0.15
     Gro
    -0.14
    asty
    -0.14
    bett
    -0.14
    .rand
    -0.14
    arily
    -0.14
    olland
    -0.14
    atts
    -0.13
    POSITIVE LOGITS
    ging
    0.65
    ged
    0.60
    ges
    0.58
    ger
    0.51
    gers
    0.49
    ge
    0.45
    GE
    0.40
    GING
    0.40
    gement
    0.40
    gest
    0.38
    Act Density 0.026%

    No Known Activations