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

    Neuronpedia

    INDEX
    Explanations

    references to feelings of disillusionment or disappointment with leadership

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     ་་
    -1.20
     itſelf
    -1.20
     myſelf
    -1.19
     Majefty
    -1.18
     Jefus
    -1.17
     Efq
    -1.17
     Theſe
    -1.16
     ſind
    -1.09
    клопе
    -1.07
     ―――――
    -1.07
    POSITIVE LOGITS
    ↵↵
    0.68
    .
    0.67
    <h2>
    0.66
    )
    0.66
    ),
    0.65
    ).
    0.63
     $\
    0.63
     (
    0.61
     A
    0.59
     
    0.59
    Act Density 0.356%

    No Known Activations