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

    Neuronpedia

    INDEX
    Explanations

    references to key figures and concepts related to political and social issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ſever
    -0.59
     ſou
    -0.58
     fallu
    -0.57
     ſta
    -0.57
     fubject
    -0.56
     myſelf
    -0.56
    iſter
    -0.56
     ſol
    -0.54
     tranſ
    -0.54
    the
    -0.54
    POSITIVE LOGITS
    es
    0.84
    ses
    0.80
    ES
    0.63
    ness
    0.62
    ess
    0.60
    hes
    0.52
    sed
    0.48
    nes
    0.47
    NESS
    0.47
    sing
    0.47
    Act Density 1.342%

    No Known Activations