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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating downward movement or transitions

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

    down to from

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     StringTokenizer
    -0.75
     ainfi
    -0.74
     increí
    -0.65
     plufieurs
    -0.65
     myſelf
    -0.65
     étoient
    -0.64
     geſ
    -0.64
    SEGUIR
    -0.63
     Geiſt
    -0.63
     yrity
    -0.63
    POSITIVE LOGITS
     down
    1.03
    down
    0.99
     Down
    0.94
    Down
    0.91
     DOWN
    0.88
    downs
    0.77
    DOWN
    0.76
     Downing
    0.71
     downs
    0.71
     ↓
    0.63
    Act Density 0.018%

    No Known Activations