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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating suggestions or recommendations

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

    suggesting actions to consider

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pelayanan
    -0.38
     oorsp
    -0.37
    transQ
    -0.36
     działal
    -0.35
    asuring
    -0.35
    accéder
    -0.35
    cyklo
    -0.34
    umerable
    -0.34
     szüks
    -0.33
    jednoc
    -0.33
    POSITIVE LOGITS
     advisable
    0.61
     supplemented
    0.60
     supplemental
    0.56
     consider
    0.56
     bör
    0.55
     recommended
    0.55
    xDB
    0.54
    0.54
    rungsseite
    0.54
     sensibly
    0.54
    Act Density 0.010%

    No Known Activations