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

    Neuronpedia

    INDEX
    Explanations

    references to variables or constants in mathematical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    MigrationBuilder
    -0.56
    oOo
    -0.56
     OnInit
    -0.52
     Blom
    -0.49
     Svetlana
    -0.48
     fubject
    -0.47
     Dupont
    -0.47
     snippetHide
    -0.46
     minimalism
    -0.46
    Katar
    -0.45
    POSITIVE LOGITS
     lemmas
    0.56
    xi
    0.53
    lem
    0.52
     lemma
    0.51
     shout
    0.50
     Democratic
    0.49
    awakeFromNib
    0.47
    Lemma
    0.46
     UID
    0.46
    UID
    0.45
    Act Density 0.474%

    No Known Activations