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

    Neuronpedia

    INDEX
    Explanations

    noun phrases indicating new or distinct concepts, particularly in academic or technical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Efq
    -1.28
    MLLoader
    -1.23
     pleaſure
    -1.20
     itſelf
    -1.16
    dafx
    -1.15
     tfsi
    -1.15
     ―――――
    -1.13
    GEBURTSDATUM
    -1.10
    ")));
    -1.08
     myſelf
    -1.05
    POSITIVE LOGITS
     
    0.89
    A
    0.80
    The
    0.73
    <strong>
    0.72
    1
    0.68
    I
    0.67
    '
    0.66
    .
    0.66
    ↵
    0.65
    To
    0.64
    Act Density 0.605%

    No Known Activations