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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating direct actions or processes

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    pr
    -0.57
     henvisninger
    -0.52
    AnchorStyles
    -0.47
    x
    -0.47
    -0.46
     <=",
    -0.46
    ud
    -0.46
    ღ
    -0.45
    &
    -0.45
      
    -0.44
    POSITIVE LOGITS
     itſelf
    0.93
    arraycopy
    0.86
     purpoſe
    0.81
     themſelves
    0.80
     himſelf
    0.80
     myſelf
    0.75
     Majefty
    0.72
     poffible
    0.72
    ]='\
    0.71
    gorithm
    0.70
    Act Density 0.040%

    No Known Activations