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

    Neuronpedia

    INDEX
    Explanations

    pronouns indicating individuals or groups

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     ―――――
    -0.67
    zema
    -0.65
     Mors
    -0.65
    FontOfSize
    -0.64
     Efq
    -0.63
    PPS
    -0.63
     nang
    -0.61
    Читати
    -0.61
     »)
    -0.60
     Majefty
    -0.60
    POSITIVE LOGITS
    Schedulers
    0.71
    исленность
    0.66
     متعلقه
    0.65
    ExtendWith
    0.61
     محفوظة
    0.60
    GrantedAuthority
    0.59
    Datuak
    0.57
    such
    0.54
     financières
    0.54
    대로
    0.54
    Act Density 0.079%

    No Known Activations