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

    Neuronpedia

    INDEX
    Explanations

    words and phrases that indicate addition or conjunction, particularly emphasizing inclusion or similarity

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

    also and similar words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    httphttps
    -0.63
    omitempty
    -0.60
    mtrl
    -0.59
    basicConfig
    -0.57
    ArgumentParser
    -0.57
    Hentet
    -0.56
    jsii
    -0.56
    rift
    -0.54
    richlet
    -0.54
    LookAnd
    -0.53
    POSITIVE LOGITS
    кож
    0.99
     также
    0.96
     Также
    0.88
    Также
    0.82
     також
    0.80
     επίσης
    0.66
     likewise
    0.58
    ępnie
    0.58
     Ebenso
    0.56
     ayrıca
    0.54
    Act Density 0.002%

    No Known Activations