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

    Neuronpedia

    INDEX
    Explanations

    references to specific numeric values or metrics

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     colorWith
    -0.71
    TestingModule
    -0.60
    AddWithValue
    -0.60
     lære
    -0.57
     ervan
    -0.57
     Roskov
    -0.56
    ']?>
    -0.56
     hurts
    -0.54
    hdys
    -0.54
    wpi
    -0.54
    POSITIVE LOGITS
     referenties
    0.67
    Rear
    0.66
     rearrange
    0.65
     Rear
    0.65
    󠁣
    0.64
     Maio
    0.63
     Falcon
    0.63
    Rhestr
    0.61
    rifuge
    0.61
     romain
    0.61
    Act Density 0.001%

    No Known Activations