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

    Neuronpedia

    INDEX
    Explanations

    phrases related to spatial relationships and proximity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ØŃÙħ
    -0.16
    hoff
    -0.16
    gency
    -0.16
    stile
    -0.15
    ebe
    -0.15
    hof
    -0.14
     Overrides
    -0.14
    lify
    -0.14
    oints
    -0.14
    842
    -0.14
    POSITIVE LOGITS
     ниÑħ
    0.18
     them
    0.15
    338
    0.15
    erial
    0.15
    obb
    0.15
     ellas
    0.15
     нее
    0.14
     mình
    0.14
    obs
    0.14
    405
    0.13
    Act Density 0.153%

    No Known Activations