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

    Neuronpedia

    INDEX
    Explanations

    instructional sentences or phrases

    oai_token-act-pair · gpt-3.5-turbo

    actions or instructions related to movement and physical activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Markets
    -0.69
     chancellor
    -0.67
    uine
    -0.67
     publisher
    -0.67
    atform
    -0.66
    leground
    -0.66
     Party
    -0.66
     multicultural
    -0.66
    ylum
    -0.65
     Abbott
    -0.65
    POSITIVE LOGITS
    izont
    1.01
     trapping
    0.88
     manoeuv
    0.85
     crou
    0.84
     traverse
    0.82
     loops
    0.81
     maneuver
    0.81
     paddle
    0.80
     directional
    0.80
     fins
    0.78
    Act Density 0.984%

    No Known Activations