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

    Neuronpedia

    INDEX
    Explanations

    references to concepts that denote responsibility or obligations

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

    Followed by a relative pronoun

    np_acts-logits-general · gemini-2.0-flash

    something followed by which or that

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    paramref
    -0.59
     greateſt
    -0.56
    __;
    -0.56
    fromnode
    -0.55
     contextLoads
    -0.54
    lossary
    -0.53
    getSystemService
    -0.53
     incluyendo
    -0.53
     Theſe
    -0.53
     ň
    -0.52
    POSITIVE LOGITS
     which
    0.74
     we
    0.68
     that
    0.64
     quite
    0.63
     rarely
    0.60
     saites
    0.60
     tutt
    0.59
     very
    0.58
     ThemeData
    0.57
     definitely
    0.57
    Act Density 0.164%

    No Known Activations