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

    Neuronpedia

    INDEX
    Explanations

    phrases that express the concept of taking action or doing something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Entered
    -0.67
     passages
    -0.65
    furt
    -0.62
     Lod
    -0.62
     Endless
    -0.59
     emptied
    -0.57
     Mell
    -0.56
     inception
    -0.55
     Polar
    -0.54
     parted
    -0.54
    POSITIVE LOGITS
     administr
    0.81
     besides
    0.80
    ????????
    0.77
     intervene
    0.74
     feas
    0.73
    atives
    0.70
    osta
    0.69
    tackle
    0.68
    icum
    0.68
     offline
    0.67
    Act Density 0.042%

    No Known Activations