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

    Neuronpedia

    INDEX
    Explanations

    references to teams or groups of people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ervo
    -0.18
    dana
    -0.17
    heid
    -0.16
    EEK
    -0.16
    oÄŁ
    -0.16
    èĬ¯
    -0.16
     Tales
    -0.15
     Inspir
    -0.15
    ÑĥлÑİ
    -0.15
    .tf
    -0.14
    POSITIVE LOGITS
     neutr
    0.16
    ä¼
    0.15
     wash
    0.15
     dich
    0.14
    ampp
    0.14
     bon
    0.14
     hel
    0.14
     Wallace
    0.14
    aml
    0.14
     sheet
    0.14
    Act Density 0.034%

    No Known Activations