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

    Neuronpedia

    INDEX
    Explanations

    quantitative data related to victims and refugees in conflicts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     itſelf
    -0.90
     pleaſure
    -0.90
     houſe
    -0.86
     Efq
    -0.86
     chofe
    -0.86
     ſeveral
    -0.84
     myſelf
    -0.83
     ſtate
    -0.81
     Majefty
    -0.81
     Monfieur
    -0.80
    POSITIVE LOGITS
     off
    0.52
    بوابة
    0.50
     "
    0.49
     di
    0.48
    exe
    0.47
     fully
    0.47
     Fla
    0.47
    shit
    0.45
     form
    0.44
     T
    0.44
    Act Density 0.027%

    No Known Activations