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

    Neuronpedia

    INDEX
    Explanations

    expressions of agreement or consensus

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ven
    -0.47
     actionTypes
    -0.47
     AUG
    -0.45
     Vener
    -0.44
    FEM
    -0.44
    ➯
    -0.43
    mechanism
    -0.43
    참고
    -0.43
     Ven
    -0.42
     snippetHide
    -0.42
    POSITIVE LOGITS
    awtextra
    0.49
     sanitarias
    0.42
     Barcelone
    0.41
     besos
    0.41
     vraie
    0.40
     verdaderas
    0.40
    Хро
    0.39
     verdaderos
    0.39
     común
    0.39
    Statistiche
    0.38
    Act Density 0.254%

    No Known Activations