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

    Neuronpedia

    INDEX
    Explanations

    expressions of concern or lack of concern

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    don’t care about

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     routines
    -0.42
     }));
    -0.42
    >)
    -0.41
    ﴿
    -0.41
    ].)
    -0.41
    ])]
    -0.40
    ]));
    -0.39
    ]));
    -0.38
     PPI
    -0.38
    }));
    -0.38
    POSITIVE LOGITS
     cared
    0.72
     propOrder
    0.68
    UnsafeEnabled
    0.66
     égale
    0.66
     frågan
    0.62
     mattered
    0.61
     Ahnung
    0.61
     banget
    0.61
     cares
    0.61
     preocupar
    0.61
    Act Density 0.006%

    No Known Activations