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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate purpose or intention

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

    just to or just for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     aikana
    -0.43
     laaj
    -0.43
     móvel
    -0.41
     årene
    -0.40
     obdob
    -0.40
     africains
    -0.40
     miejsc
    -0.40
     zimowa
    -0.40
     budow
    -0.39
     Consultez
    -0.39
    POSITIVE LOGITS
     autorytatywna
    0.79
    +#+#
    0.68
     JUST
    0.68
    just
    0.64
    ftagPool
    0.63
    WithIOException
    0.61
    justin
    0.61
    JUST
    0.60
    Just
    0.60
    SizeMode
    0.58
    Act Density 0.011%

    No Known Activations