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

    Neuronpedia

    INDEX
    Explanations

    formatting symbols and punctuation used in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oneofs
    -0.56
    Personendaten
    -0.53
    Vidite
    -0.53
     absolu
    -0.51
    lioni
    -0.50
     TestBed
    -0.50
     farlo
    -0.49
    دانشنامهٔ
    -0.48
    DataAnnotations
    -0.48
     audited
    -0.48
    POSITIVE LOGITS
    ########.
    0.65
    +#+#
    0.59
    kuuta
    0.57
     muualla
    0.56
    Carriera
    0.55
     الدولى
    0.55
    Hentet
    0.55
    crombie
    0.54
    MigrationBuilder
    0.54
     виправивши
    0.52
    Act Density 0.151%

    No Known Activations