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

    Neuronpedia

    INDEX
    Explanations

    locations indicated by a distance away from a specific point

    oai_token-act-pair · gpt-3.5-turbo

    phrases describing distance or proximity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adobe
    -0.76
    ergy
    -0.70
    ãĤ±
    -0.68
    ogly
    -0.68
    icer
    -0.62
    uala
    -0.60
    Sense
    -0.60
    itely
    -0.60
    +=
    -0.59
    ahime
    -0.59
    POSITIVE LOGITS
     from
    1.11
    from
    0.84
     FROM
    0.82
     geographically
    0.76
     away
    0.74
    outheast
    0.71
    sighted
    0.71
     located
    0.68
     From
    0.68
     ahead
    0.67
    Act Density 0.076%

    No Known Activations