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

    Neuronpedia

    INDEX
    Explanations

    comparisons indicating preference or choices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ály
    -0.15
    ropolis
    -0.14
    erland
    -0.14
    voje
    -0.14
    EditingStyle
    -0.14
    chg
    -0.14
     erken
    -0.13
    eso
    -0.13
    ÑĢÑĥб
    -0.13
    tran
    -0.13
    POSITIVE LOGITS
     being
    0.37
    being
    0.30
     having
    0.29
     Being
    0.27
    Being
    0.24
     sendo
    0.23
    having
    0.22
     relying
    0.21
     usual
    0.19
     resort
    0.19
    Act Density 0.037%

    No Known Activations