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

    Neuronpedia

    INDEX
    Explanations

    phrases related to approaching or standing near a target

    oai_token-act-pair · gpt-3.5-turbo

    phrases that describe physical movement towards a location or object

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hare
    -0.70
    rences
    -0.69
     Perspective
    -0.65
    Works
    -0.64
    oche
    -0.63
    United
    -0.61
     Controlled
    -0.60
    green
    -0.60
    hops
    -0.59
    Green
    -0.59
    POSITIVE LOGITS
     defend
    0.81
     compensate
    0.80
     date
    0.75
    pload
    0.74
     Leilan
    0.70
     baseline
    0.70
     ensure
    0.69
    dos
    0.69
     pasture
    0.68
     insure
    0.65
    Act Density 0.049%

    No Known Activations