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

    Neuronpedia

    INDEX
    Explanations

    verbs related to movement and change

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     retreat
    -0.69
     chooses
    -0.64
     pilgr
    -0.62
     trek
    -0.62
     lookout
    -0.62
     prow
    -0.61
    ointed
    -0.61
    iling
    -0.60
    gart
    -0.60
    gow
    -0.60
    POSITIVE LOGITS
     nicely
    0.81
    UE
    0.73
    netflix
    0.72
     smoothly
    0.71
    tones
    0.69
     exactly
    0.69
    ĸļ
    0.68
     satisf
    0.68
    tails
    0.65
    Attach
    0.65
    Act Density 1.619%

    No Known Activations