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

    Neuronpedia

    INDEX
    Explanations

    terms related to measurement and intervals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     gostar
    -0.42
     powin
    -0.42
     paraître
    -0.40
    retudo
    -0.38
     cancelamento
    -0.37
    🖨
    -0.35
     estimés
    -0.35
     Boletín
    -0.35
     vern
    -0.34
     Hogar
    -0.34
    POSITIVE LOGITS
     intermediary
    0.95
     mid
    0.90
     intermediate
    0.89
    mid
    0.87
    Mid
    0.86
     Intermediate
    0.85
     Mid
    0.85
     Midway
    0.82
    Intermediate
    0.82
     mellem
    0.81
    Act Density 1.523%

    No Known Activations