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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating movement or direction related to returning or going to different places or states

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

    take to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AssemblyTitle
    -0.63
    <?
    -0.42
     שוליים
    -0.42
    utek
    -0.39
    limia
    -0.37
     оригіналу
    -0.37
    künfte
    -0.36
    rime
    -0.36
    RTLI
    -0.36
    面
    -0.36
    POSITIVE LOGITS
     taken
    0.56
     take
    0.56
     TAKE
    0.55
    taken
    0.52
     Taken
    0.52
     Take
    0.51
    take
    0.51
     TAKEN
    0.50
    Taken
    0.50
     takes
    0.50
    Act Density 0.030%

    No Known Activations