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

    Neuronpedia

    INDEX
    Explanations

    instances of location-related words, particularly "here" and "there."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gis
    -0.18
    raÄį
    -0.15
    ër
    -0.15
    ëĮ
    -0.14
    lass
    -0.14
    illy
    -0.14
     feu
    -0.14
    elay
    -0.14
    theid
    -0.14
    wap
    -0.14
    POSITIVE LOGITS
    zelf
    0.16
    <article
    0.14
     sole
    0.14
    abant
    0.14
    adian
    0.13
     gun
    0.13
     Gun
    0.13
    åĨł
    0.13
     mechan
    0.13
    unga
    0.13
    Act Density 0.020%

    No Known Activations