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

    Neuronpedia

    INDEX
    Explanations

    actions or events related to physical motion or activity

    oai_token-act-pair · gpt-3.5-turbo

    action-oriented verbs and phrases describing dynamic movements or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gui
    -0.72
    redo
    -0.69
    forming
    -0.69
    thinking
    -0.66
    aun
    -0.65
    cluding
    -0.65
    ena
    -0.65
    tel
    -0.64
    croft
    -0.64
    pleting
    -0.63
    POSITIVE LOGITS
     hay
    0.80
     furiously
    0.75
     cough
    0.67
     spree
    0.66
     frantically
    0.65
     merry
    0.64
     brisk
    0.60
     bowls
    0.59
     suspic
    0.59
     slang
    0.59
    Act Density 0.344%

    No Known Activations