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

    Neuronpedia

    INDEX
    Explanations

    negative expressions or sentiments regarding societal or political issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    áp
    -0.14
    idade
    -0.14
    HEET
    -0.13
    undred
    -0.13
    isol
    -0.13
    .ev
    -0.13
     arch
    -0.13
    iti
    -0.13
    [$_
    -0.13
    casting
    -0.13
    POSITIVE LOGITS
    лаÑĪ
    0.17
    audi
    0.16
    utzer
    0.15
    emailer
    0.14
    asher
    0.14
    berman
    0.14
     Adults
    0.14
    è¡£
    0.14
    _texts
    0.14
    geber
    0.14
    Act Density 0.091%

    No Known Activations