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

    Neuronpedia

    INDEX
    Explanations

    phrases related to performing tasks manually or electronically

    oai_token-act-pair · gpt-3.5-turbo

    references to manual tasks or processes versus automated ones

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĸļ
    -0.89
    addons
    -0.78
    iens
    -0.76
     Coverage
    -0.75
     Passage
    -0.74
     Parables
    -0.73
    rug
    -0.73
    soon
    -0.70
     Winds
    -0.70
     Intent
    -0.67
    POSITIVE LOGITS
     configured
    0.87
     operated
    0.81
     manually
    0.80
     controlled
    0.79
     contro
    0.78
     calibr
    0.75
     programmed
    0.74
     scaven
    0.74
     towed
    0.73
     synthes
    0.73
    Act Density 0.021%

    No Known Activations