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

    Neuronpedia

    INDEX
    Explanations

    words related to physical actions or tools

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

    tac- words and continuations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ê
    -0.45
     Gend
    -0.43
    |/
    -0.42
    Gro
    -0.40
    meri
    -0.40
    ��������
    -0.40
     MDM
    -0.38
    orer
    -0.38
    WEBPACK
    -0.38
     famí
    -0.38
    POSITIVE LOGITS
     tack
    2.34
     Tack
    2.02
    tack
    1.91
    Tack
    1.89
     tac
    1.23
     tacky
    1.20
     Tac
    1.10
    Tac
    1.06
     tact
    1.05
     Tackle
    0.99
    Act Density 0.005%

    No Known Activations