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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate collaboration or connection between entities

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

    phrases like "along with"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RefNanny
    -0.42
    multicolumn
    -0.42
     circumstances
    -0.34
     ujednoznacz
    -0.33
     ferro
    -0.32
     Ferro
    -0.31
     yyb
    -0.31
     wherea
    -0.31
    scope
    -0.31
     ничего
    -0.30
    POSITIVE LOGITS
    ammans
    0.70
    Together
    0.64
     Junto
    0.62
     Together
    0.60
    OGND
    0.59
    Alongside
    0.59
     Alongside
    0.58
     Along
    0.57
     juntamente
    0.57
     Avec
    0.56
    Act Density 0.010%

    No Known Activations