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

    Neuronpedia

    INDEX
    Explanations

    phrases relating to movement or action in a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    man ran, we lost

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    LEncoder
    -0.42
    astify
    -0.35
     egyéb
    -0.32
     normalen
    -0.32
    率
    -0.32
    چون
    -0.30
    ต่อไป
    -0.30
    Referanser
    -0.29
    ือง
    -0.28
    ねぇ
    -0.28
    POSITIVE LOGITS
     surla
    0.70
    ⟬
    0.62
     Italijanski
    0.56
     становника
    0.54
     snippetHide
    0.54
    verifyException
    0.50
     Infórmanos
    0.49
     iſt
    0.48
     propOrder
    0.47
     Мексичка
    0.47
    Act Density 0.012%

    No Known Activations