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

    Neuronpedia

    INDEX
    Explanations

    words indicating economic responsibility or implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    çĶ
    -0.15
    ego
    -0.14
    lak
    -0.14
     Bow
    -0.14
     Goldberg
    -0.13
    /us
    -0.13
    सन
    -0.13
    ullan
    -0.13
    ein
    -0.13
    alk
    -0.13
    POSITIVE LOGITS
    arty
    0.16
    ilon
    0.15
     Pound
    0.15
    ULA
    0.15
    angler
    0.14
    765
    0.14
     Marty
    0.14
    idad
    0.14
    -pattern
    0.14
    kor
    0.14
    Act Density 0.465%

    No Known Activations