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

    Neuronpedia

    INDEX
    Explanations

    words associated with directional terms, particularly focused on "left" and "right."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hir
    -0.17
    ungle
    -0.14
    oir
    -0.14
    edo
    -0.14
    :animated
    -0.14
    åĨµ
    -0.14
     MainAxisAlignment
    -0.14
    idia
    -0.14
    817
    -0.14
    ombat
    -0.14
    POSITIVE LOGITS
    y
    0.21
    ies
    0.16
    yg
    0.15
    ye
    0.15
    anka
    0.15
     J
    0.15
    yx
    0.15
     G
    0.14
    agn
    0.14
    åŃĹ
    0.14
    Act Density 0.016%

    No Known Activations