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

    Neuronpedia

    INDEX
    Explanations

    word endings that suggest an action or characteristic in multiple languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arangay
    -0.81
     anún
    -0.81
     dovre
    -0.81
     argint
    -0.79
    iffance
    -0.78
    ambién
    -0.74
     împre
    -0.74
    erintah
    -0.73
    alakip
    -0.73
    ientras
    -0.73
    POSITIVE LOGITS
    Portale
    0.54
    TokenNameLPAREN
    0.52
    arraycopy
    0.50
    []{"
    0.47
    μβρίου
    0.47
     Obrador
    0.45
    ScopeManager
    0.45
     Regent
    0.44
     regent
    0.43
    ⓧ
    0.43
    Act Density 0.023%

    No Known Activations