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

    Neuronpedia

    INDEX
    Explanations

    verbs and their forms, particularly focusing on the verb "to be" and its conjugations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    MigrationBuilder
    -0.40
    something
    -0.38
     Autorizaciones
    -0.35
    gl
    -0.34
     something
    -0.34
    NOTHING
    -0.33
    Nothing
    -0.33
     صوتيه
    -0.33
    nothing
    -0.32
    ye
    -0.32
    POSITIVE LOGITS
     talking
    1.02
     trying
    0.95
     proposing
    0.90
     discussing
    0.87
     referring
    0.87
     dealing
    0.86
     asking
    0.85
     describing
    0.85
     doing
    0.84
     using
    0.82
    Act Density 0.426%

    No Known Activations