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

    Neuronpedia

    INDEX
    Explanations

    negative connotations or criticisms regarding various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dale
    -0.17
    838
    -0.15
    lez
    -0.15
    758
    -0.15
    endon
    -0.14
    831
    -0.14
    ingroup
    -0.14
    ISMATCH
    -0.14
    quivo
    -0.14
    ãĤĤãģ£ãģ¨
    -0.14
    POSITIVE LOGITS
    ger
    0.21
    dest
    0.18
     habit
    0.17
     Hab
    0.16
    ulence
    0.16
    sst
    0.15
    GER
    0.14
    umper
    0.14
     hab
    0.14
    ulent
    0.14
    Act Density 0.091%

    No Known Activations