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

    Neuronpedia

    INDEX
    Explanations

    words related to legal charges or accusations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mor
    -0.51
    zen
    -0.50
     ter
    -0.50
     tires
    -0.50
     hair
    -0.50
    ny
    -0.49
    el
    -0.49
    cu
    -0.48
     cess
    -0.48
     é
    -0.47
    POSITIVE LOGITS
     zijne
    0.63
     صوتيه
    0.60
     kautta
    0.59
     poffible
    0.56
     maravilloso
    0.56
     gustaba
    0.56
     mío
    0.55
     fufficient
    0.54
     maravillosa
    0.54
     regalías
    0.54
    Act Density 0.149%

    No Known Activations