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

    Neuronpedia

    INDEX
    Explanations

    instances of location or directional terms related to places and movements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enis
    -0.18
    anco
    -0.16
    antom
    -0.15
    pie
    -0.15
    ãģ¯ãģļ
    -0.15
    hole
    -0.14
    /trunk
    -0.14
    aln
    -0.14
    annel
    -0.14
    olley
    -0.14
    POSITIVE LOGITS
     nearby
    0.15
    iro
    0.15
    IOR
    0.14
     plastic
    0.14
     coupon
    0.14
     incon
    0.14
    raith
    0.14
     Dice
    0.14
    077
    0.14
    838
    0.14
    Act Density 0.305%

    No Known Activations