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

    Neuronpedia

    INDEX
    Explanations

    concepts related to limitations and expectations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    værende
    -0.58
    AddWithValue
    -0.56
    MLLoader
    -0.53
    ISupport
    -0.51
     preferido
    -0.49
    Outras
    -0.48
    发表于
    -0.47
     egyes
    -0.47
     différente
    -0.46
     précédente
    -0.45
    POSITIVE LOGITS
     kind
    1.41
     sort
    1.15
     type
    1.08
    kind
    1.04
     kinds
    1.02
     kinda
    0.90
    kinds
    0.89
     level
    0.88
     sorta
    0.84
     sorts
    0.84
    Act Density 0.360%

    No Known Activations